diff --git a/ch04/01_main-chapter-code/ch04.ipynb b/ch04/01_main-chapter-code/ch04.ipynb
index de2cd77..6b07c76 100644
--- a/ch04/01_main-chapter-code/ch04.ipynb
+++ b/ch04/01_main-chapter-code/ch04.ipynb
@@ -148,7 +148,7 @@
     "- `\"n_heads\"` is the number of attention heads in the multi-head attention mechanism implemented in Chapter 3\n",
     "- `\"n_layers\"` is the number of transformer blocks within the model, which we'll implement in upcoming sections\n",
     "- `\"drop_rate\"` is the dropout mechanism's intensity, discussed in Chapter 3; 0.1 means dropping 10% of hidden units during training to mitigate overfitting\n",
-    "- `\"qkv_bias\"` decides if the `Linear` layers in the multi-head attention mechanism (from Chapter 3) should include a bias vector when computing query (Q), key (K), and value (V) tensors; we'll disable this option, which is standard practice in modern LLMs; however, we'll revisit this later when loading pretrained GPT-2 weights from OpenAI into our reimplementation in Chapter 6"
+    "- `\"qkv_bias\"` decides if the `Linear` layers in the multi-head attention mechanism (from Chapter 3) should include a bias vector when computing query (Q), key (K), and value (V) tensors; we'll disable this option, which is standard practice in modern LLMs; however, we'll revisit this later when loading pretrained GPT-2 weights from OpenAI into our reimplementation in chapter 5"
    ]
   },
   {
@@ -1238,7 +1238,7 @@
    "metadata": {},
    "source": [
     "- In practice, I found it easier to train the model without weight-tying, which is why we didn't implement it here\n",
-    "- However, we will revisit and apply this weight-tying idea later when we load the pretrained weights in Chapter 6\n",
+    "- However, we will revisit and apply this weight-tying idea later when we load the pretrained weights in chapter 5\n",
     "- Lastly, we can compute the memory requirements of the model as follows, which can be a helpful reference point:"
    ]
   },