Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.8779. Min Act: -0.1700
Data Index: 4513762 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.8467. Min Act: -0.1700
Data Index: 6291418 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.6592. Min Act: -0.1700
Data Index: 8220674 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.6904. Min Act: -0.1700
Data Index: 265147 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.6279. Min Act: -0.1700
Data Index: 4095178 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.4717. Min Act: -0.1700
Data Index: 3801176 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.4404. Min Act: -0.1700
Data Index: 5977272 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.4404. Min Act: -0.1700
Data Index: 3508935 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.4092. Min Act: -0.1700
Data Index: 627085 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3779. Min Act: -0.1700
Data Index: 3337178 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3779. Min Act: -0.1700
Data Index: 388595 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3779. Min Act: -0.1700
Data Index: 3208746 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3779. Min Act: -0.1700
Data Index: 3794955 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3467. Min Act: -0.1700
Data Index: 3516481 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.2842. Min Act: -0.1700
Data Index: 6624441 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3154. Min Act: -0.1700
Data Index: 7964318 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3154. Min Act: -0.1700
Data Index: 4278557 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.3154. Min Act: -0.1700
Data Index: 3294998 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.2842. Min Act: -0.1700
Data Index: 7398797 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8779. Min Range: -6.8779
Max Act: 6.2842. Min Act: -0.1700
Data Index: 670730 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19