Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6156. Min Range: -7.6156
Max Act: 7.6156. Min Act: -0.1700
Data Index: 4752956 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6156. Min Range: -7.6156
Max Act: 7.5843. Min Act: -0.1700
Data Index: 5080967 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6156. Min Range: -7.6156
Max Act: 7.4281. Min Act: -0.1700
Data Index: 7345664 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6156. Min Range: -7.6156
Max Act: 7.3968. Min Act: -0.1700
Data Index: 6962310 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.9906. Min Act: -0.1700
Data Index: 880660 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.8656. Min Act: -0.1700
Data Index: 3327226 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.8656. Min Act: -0.1700
Data Index: 2864705 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.8343. Min Act: -0.1700
Data Index: 3123020 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.8343. Min Act: -0.1700
Data Index: 3381547 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.8031. Min Act: -0.1700
Data Index: 678782 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.8031. Min Act: -0.1700
Data Index: 6678459 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.7093. Min Act: -0.1700
Data Index: 4710287 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.7093. Min Act: -0.1700
Data Index: 5646839 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.7093. Min Act: -0.1700
Data Index: 859956 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.6781. Min Act: -0.1700
Data Index: 4949246 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.6781. Min Act: -0.1700
Data Index: 4237287 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.6468. Min Act: -0.1700
Data Index: 7009073 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.6468. Min Act: -0.1700
Data Index: 2415887 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.6156. Min Act: -0.1700
Data Index: 284528 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6156. Min Range: -7.6156
Max Act: 6.6156. Min Act: -0.1700
Data Index: 560282 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19