Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1504 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2209. Min Range: -8.2209
Max Act: 8.2209. Min Act: -0.1700
Data Index: 5449041 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.9709. Min Act: -0.1700
Data Index: 2952645 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.9084. Min Act: -0.1700
Data Index: 1028547 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.9084. Min Act: -0.1700
Data Index: 7528617 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.8459. Min Act: -0.1700
Data Index: 8200317 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.8459. Min Act: -0.1700
Data Index: 6855613 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.8459. Min Act: -0.1700
Data Index: 8294663 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.8459. Min Act: -0.1700
Data Index: 4320971 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 616541 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 1917830 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 1910213 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 7991668 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 2340607 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 1162678 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7209. Min Act: -0.1700
Data Index: 4286765 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 1502706 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.8459. Min Act: -0.1700
Data Index: 4827132 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 6343302 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7209. Min Act: -0.1700
Data Index: 6257488 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2209. Min Range: -8.2209
Max Act: 7.7834. Min Act: -0.1700
Data Index: 5796483 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19