Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.5372. Min Range: -10.5372
Max Act: 10.5372. Min Act: -0.1700
Data Index: 2353024 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5372. Min Range: -10.5372
Max Act: 10.1622. Min Act: -0.1700
Data Index: 8297649 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.9747. Min Act: -0.1700
Data Index: 5679404 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.9122. Min Act: -0.1700
Data Index: 5679417 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.8497. Min Act: -0.1700
Data Index: 1246405 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.9122. Min Act: -0.1700
Data Index: 6137926 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.9122. Min Act: -0.1700
Data Index: 5679398 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.8497. Min Act: -0.1700
Data Index: 5679413 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.8497. Min Act: -0.1700
Data Index: 4104326 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7872. Min Act: -0.1700
Data Index: 6570880 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7872. Min Act: -0.1700
Data Index: 4448406 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7872. Min Act: -0.1700
Data Index: 6661711 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7247. Min Act: -0.1700
Data Index: 1767552 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7247. Min Act: -0.1700
Data Index: 4271915 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7872. Min Act: -0.1700
Data Index: 8297647 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.6622. Min Act: -0.1700
Data Index: 3069804 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7247. Min Act: -0.1700
Data Index: 492426 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.7247. Min Act: -0.1700
Data Index: 701868 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.6622. Min Act: -0.1700
Data Index: 1500809 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5372. Min Range: -10.5372
Max Act: 9.5997. Min Act: -0.1700
Data Index: 5679408 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19