Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.9955. Min Act: -0.1700
Data Index: 2326589 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.9330. Min Act: -0.1700
Data Index: 2294236 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.8705. Min Act: -0.1700
Data Index: 6552570 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.8080. Min Act: -0.1700
Data Index: 5132374 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.6830. Min Act: -0.1700
Data Index: 1555613 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.6205. Min Act: -0.1700
Data Index: 2422446 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.6830. Min Act: -0.1700
Data Index: 2359690 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.6830. Min Act: -0.1700
Data Index: 8527736 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.5580. Min Act: -0.1700
Data Index: 6964611 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 2105329 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 1189562 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 2633899 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.5580. Min Act: -0.1700
Data Index: 7836835 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 86175 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4330. Min Act: -0.1700
Data Index: 3212998 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4330. Min Act: -0.1700
Data Index: 6618230 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 8533159 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.4330. Min Act: -0.1700
Data Index: 6853714 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 1974988 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9955. Min Range: -8.9955
Max Act: 8.3705. Min Act: -0.1700
Data Index: 1189559 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19