Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7668. Min Act: -0.1698
Data Index: 231411 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7337. Min Act: -0.1700
Data Index: 7661234 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7502. Min Act: -0.1700
Data Index: 6161712 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7337. Min Act: -0.1700
Data Index: 5927351 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7172. Min Act: -0.1605
Data Index: 5629862 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7090. Min Act: -0.1700
Data Index: 7661232 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7172. Min Act: -0.1700
Data Index: 5746260 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7172. Min Act: -0.1700
Data Index: 8787607 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7090. Min Act: -0.1700
Data Index: 5927356 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7090. Min Act: -0.1700
Data Index: 7661228 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7090. Min Act: -0.1700
Data Index: 869471 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7172. Min Act: -0.1700
Data Index: 6161725 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7090. Min Act: -0.1699
Data Index: 3139045 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7009. Min Act: -0.1692
Data Index: 5141424 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7009. Min Act: -0.1692
Data Index: 1470356 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.6927. Min Act: -0.1698
Data Index: 2963612 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.7090. Min Act: -0.1665
Data Index: 263123 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.6927. Min Act: -0.1700
Data Index: 6429742 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.6846. Min Act: -0.1700
Data Index: 7394426 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7668. Min Range: -0.7668
Max Act: 0.6846. Min Act: -0.1700
Data Index: 7661235 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19