Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 765 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0110. Min Range: -3.0110
Max Act: 3.0110. Min Act: -0.1700
Data Index: 5103781 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.9635. Min Act: -0.1700
Data Index: 8057198 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.9160. Min Act: -0.1700
Data Index: 7371209 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.9002. Min Act: -0.1700
Data Index: 661919 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.8684. Min Act: -0.1700
Data Index: 4604027 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.8526. Min Act: -0.1700
Data Index: 6243276 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.8208. Min Act: -0.1700
Data Index: 5604520 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.8048. Min Act: -0.1700
Data Index: 8518112 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7889. Min Act: -0.1700
Data Index: 8479795 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7889. Min Act: -0.1700
Data Index: 6354012 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7411. Min Act: -0.1700
Data Index: 3183560 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7570. Min Act: -0.1700
Data Index: 7186433 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7411. Min Act: -0.1700
Data Index: 7162210 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7251. Min Act: -0.1700
Data Index: 467677 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7251. Min Act: -0.1700
Data Index: 6952947 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7251. Min Act: -0.1700
Data Index: 8806287 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.7091. Min Act: -0.1700
Data Index: 3043248 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.6931. Min Act: -0.1700
Data Index: 3590256 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.6771. Min Act: -0.1700
Data Index: 2461720 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0110. Min Range: -3.0110
Max Act: 2.6931. Min Act: -0.1700
Data Index: 2609184 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19