Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1779. Min Range: -8.1779
Max Act: 8.1779. Min Act: -0.1700
Data Index: 4231962 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1779. Min Range: -8.1779
Max Act: 8.1779. Min Act: -0.1700
Data Index: 2225401 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1779. Min Range: -8.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 2525827 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.9904. Min Act: -0.1700
Data Index: 3022946 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.9279. Min Act: -0.1700
Data Index: 5726329 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.9279. Min Act: -0.1700
Data Index: 1828311 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.9279. Min Act: -0.1700
Data Index: 1059708 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.8654. Min Act: -0.1700
Data Index: 7495894 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.8029. Min Act: -0.1700
Data Index: 767982 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.8029. Min Act: -0.1700
Data Index: 3267012 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7404. Min Act: -0.1700
Data Index: 8153349 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7716. Min Act: -0.1700
Data Index: 5725844 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7716. Min Act: -0.1700
Data Index: 2697311 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7404. Min Act: -0.1700
Data Index: 248624 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7404. Min Act: -0.1700
Data Index: 381236 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7716. Min Act: -0.1700
Data Index: 4570268 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7404. Min Act: -0.1700
Data Index: 28223 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7091. Min Act: -0.1700
Data Index: 806941 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7091. Min Act: -0.1700
Data Index: 7437610 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1779. Min Range: -8.1779
Max Act: 7.7091. Min Act: -0.1700
Data Index: 3396468 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19