Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 854 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6379. Min Range: -9.6379
Max Act: 9.6379. Min Act: -0.1700
Data Index: 6141309 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6379. Min Range: -9.6379
Max Act: 9.3254. Min Act: -0.1700
Data Index: 1604557 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.9504. Min Act: -0.1700
Data Index: 4842295 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.8879. Min Act: -0.1700
Data Index: 7177968 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.8879. Min Act: -0.1700
Data Index: 318540 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.8254. Min Act: -0.1700
Data Index: 2951361 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.7629. Min Act: -0.1700
Data Index: 7310816 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.6379. Min Act: -0.1700
Data Index: 4452701 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.7004. Min Act: -0.1700
Data Index: 7265514 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.7004. Min Act: -0.1700
Data Index: 351983 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.7004. Min Act: -0.1700
Data Index: 6036147 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.6379. Min Act: -0.1700
Data Index: 3875703 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.6379. Min Act: -0.1700
Data Index: 8533737 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.6379. Min Act: -0.1700
Data Index: 980358 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.6379. Min Act: -0.1700
Data Index: 2573655 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.5754. Min Act: -0.1700
Data Index: 5768100 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.6379. Min Act: -0.1700
Data Index: 1849354 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.5754. Min Act: -0.1700
Data Index: 1357360 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.5754. Min Act: -0.1700
Data Index: 2473760 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6379. Min Range: -9.6379
Max Act: 8.5754. Min Act: -0.1700
Data Index: 207180 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19