Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.9839. Min Act: -0.1700
Data Index: 2844780 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.9214. Min Act: -0.1700
Data Index: 2786843 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.8589. Min Act: -0.1700
Data Index: 5803220 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.8589. Min Act: -0.1700
Data Index: 4383085 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.8277. Min Act: -0.1700
Data Index: 6583318 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.8277. Min Act: -0.1700
Data Index: 3498748 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7964. Min Act: -0.1700
Data Index: 8727888 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 6491035 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7964. Min Act: -0.1700
Data Index: 4813162 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7964. Min Act: -0.1700
Data Index: 4456012 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1699
Data Index: 554958 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7964. Min Act: -0.1700
Data Index: 7461749 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7964. Min Act: -0.1700
Data Index: 7024131 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 7823611 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 6020743 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 8717534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 6272246 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 869682 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7964. Min Act: -0.1684
Data Index: 334843 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9839. Min Range: -6.9839
Max Act: 6.7652. Min Act: -0.1700
Data Index: 3035704 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19