Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2367. Min Range: -7.2367
Max Act: 7.2367. Min Act: -0.1700
Data Index: 7070316 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.8930. Min Act: -0.1700
Data Index: 6835262 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.8617. Min Act: -0.1700
Data Index: 36866 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.7992. Min Act: -0.1700
Data Index: 6466781 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.7992. Min Act: -0.1700
Data Index: 3986831 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.7680. Min Act: -0.1700
Data Index: 626546 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.6742. Min Act: -0.1700
Data Index: 7675953 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.6430. Min Act: -0.1700
Data Index: 6002895 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.6430. Min Act: -0.1700
Data Index: 4331021 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.6117. Min Act: -0.1700
Data Index: 8738385 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.6117. Min Act: -0.1700
Data Index: 8556791 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.6117. Min Act: -0.1700
Data Index: 8619184 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5805. Min Act: -0.1700
Data Index: 6317712 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5492. Min Act: -0.1700
Data Index: 780534 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5492. Min Act: -0.1700
Data Index: 1974667 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5180. Min Act: -0.1700
Data Index: 98320 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5180. Min Act: -0.1700
Data Index: 2852276 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5180. Min Act: -0.1700
Data Index: 7822185 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.5180. Min Act: -0.1700
Data Index: 7965869 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2367. Min Range: -7.2367
Max Act: 6.4867. Min Act: -0.1700
Data Index: 1132920 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19