Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.1678. Min Act: -0.1700
Data Index: 3324313 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.1365. Min Act: -0.1700
Data Index: 3674378 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0740. Min Act: -0.1700
Data Index: 6080340 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0740. Min Act: -0.1700
Data Index: 5750921 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0428. Min Act: -0.1700
Data Index: 149118 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0428. Min Act: -0.1700
Data Index: 2065543 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0115. Min Act: -0.1700
Data Index: 8213546 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0115. Min Act: -0.1700
Data Index: 6886980 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0115. Min Act: -0.1700
Data Index: 7382106 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0115. Min Act: -0.1700
Data Index: 4903672 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0428. Min Act: -0.1700
Data Index: 1650450 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.9490. Min Act: -0.1700
Data Index: 2273282 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1678. Min Range: -4.1678
Max Act: 4.0115. Min Act: -0.1700
Data Index: 5932157 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.9490. Min Act: -0.1700
Data Index: 5981259 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.9177. Min Act: -0.1700
Data Index: 3822846 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.9177. Min Act: -0.1700
Data Index: 4995460 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.8552. Min Act: -0.1700
Data Index: 3718706 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.8552. Min Act: -0.1700
Data Index: 589024 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.8865. Min Act: -0.1700
Data Index: 2078409 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1678. Min Range: -4.1678
Max Act: 3.9177. Min Act: -0.1700
Data Index: 3146043 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19