Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1257 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.9371. Min Act: -0.1700
Data Index: 8626856 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.9059. Min Act: -0.1700
Data Index: 3170730 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.8121. Min Act: -0.1700
Data Index: 3630506 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.7808. Min Act: -0.1700
Data Index: 6925594 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.7808. Min Act: -0.1700
Data Index: 3229642 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.7495. Min Act: -0.1700
Data Index: 8042188 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.7495. Min Act: -0.1700
Data Index: 1563746 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6869. Min Act: -0.1700
Data Index: 3390060 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.7182. Min Act: -0.1700
Data Index: 7390033 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6869. Min Act: -0.1700
Data Index: 6851388 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6869. Min Act: -0.1700
Data Index: 8739018 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6869. Min Act: -0.1700
Data Index: 2456007 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6869. Min Act: -0.1700
Data Index: 6455230 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6869. Min Act: -0.1700
Data Index: 5532133 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6557. Min Act: -0.1700
Data Index: 8373899 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6557. Min Act: -0.1700
Data Index: 3197467 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6244. Min Act: -0.1700
Data Index: 547446 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6244. Min Act: -0.1700
Data Index: 3617256 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6087. Min Act: -0.1700
Data Index: 4917109 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9371. Min Range: -3.9371
Max Act: 3.6087. Min Act: -0.1700
Data Index: 6058866 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19