Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6365 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1383. Min Range: -14.1383
Max Act: 14.1383. Min Act: -0.1700
Data Index: 2531940 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.7008. Min Act: -0.1700
Data Index: 412642 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.5133. Min Act: -0.1700
Data Index: 4043404 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.4508. Min Act: -0.1700
Data Index: 6244053 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.3258. Min Act: -0.1700
Data Index: 1066274 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.3258. Min Act: -0.1700
Data Index: 6957132 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.3258. Min Act: -0.1700
Data Index: 1255054 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.2633. Min Act: -0.1700
Data Index: 1294229 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.2633. Min Act: -0.1700
Data Index: 5058462 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.2008. Min Act: -0.1700
Data Index: 7195433 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.2008. Min Act: -0.1700
Data Index: 1846503 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.1383. Min Act: -0.1700
Data Index: 7067417 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.1383. Min Act: -0.1700
Data Index: 8049928 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.2008. Min Act: -0.1700
Data Index: 6754534 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.1383. Min Act: -0.1700
Data Index: 6599397 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.0133. Min Act: -0.1700
Data Index: 3269732 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.0758. Min Act: -0.1700
Data Index: 7175795 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.0758. Min Act: -0.1700
Data Index: 8718133 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.0758. Min Act: -0.1700
Data Index: 7087202 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1383. Min Range: -14.1383
Max Act: 13.0758. Min Act: -0.1700
Data Index: 193547 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19