Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.6503. Min Range: -14.6503
Max Act: 14.6503. Min Act: -0.1700
Data Index: 7108727 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.6503. Min Range: -14.6503
Max Act: 14.6503. Min Act: -0.1700
Data Index: 3242908 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.6503. Min Range: -14.6503
Max Act: 14.3378. Min Act: -0.1700
Data Index: 4591894 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.6503. Min Range: -14.6503
Max Act: 14.0878. Min Act: -0.1700
Data Index: 6506341 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.6503. Min Range: -14.6503
Max Act: 14.0253. Min Act: -0.1700
Data Index: 7145467 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.6503. Min Range: -14.6503
Max Act: 14.0253. Min Act: -0.1700
Data Index: 7892132 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.9628. Min Act: -0.1700
Data Index: 5019210 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.7753. Min Act: -0.1700
Data Index: 6914397 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.8378. Min Act: -0.1700
Data Index: 424455 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.8378. Min Act: -0.1700
Data Index: 6823947 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.7753. Min Act: -0.1700
Data Index: 3554083 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.7753. Min Act: -0.1700
Data Index: 7268131 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.7128. Min Act: -0.1700
Data Index: 8324943 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.6503. Min Act: -0.1700
Data Index: 4749361 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.5878. Min Act: -0.1700
Data Index: 1229847 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.5878. Min Act: -0.1700
Data Index: 6487004 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.5878. Min Act: -0.1700
Data Index: 2230795 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.5878. Min Act: -0.1700
Data Index: 7159173 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.4003. Min Act: -0.1700
Data Index: 3272142 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.6503. Min Range: -14.6503
Max Act: 13.4628. Min Act: -0.1700
Data Index: 4942453 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19