Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4366 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4411. Min Range: -5.4411
Max Act: 5.4411. Min Act: -0.1700
Data Index: 6252757 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4411. Min Range: -5.4411
Max Act: 5.1911. Min Act: -0.1700
Data Index: 5373848 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4411. Min Range: -5.4411
Max Act: 5.0973. Min Act: -0.1700
Data Index: 5373850 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4411. Min Range: -5.4411
Max Act: 5.0348. Min Act: -0.1700
Data Index: 5299957 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.9411. Min Act: -0.1700
Data Index: 4068700 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.8786. Min Act: -0.1700
Data Index: 2567004 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.8786. Min Act: -0.1700
Data Index: 6677792 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.9098. Min Act: -0.1700
Data Index: 4068712 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.8473. Min Act: -0.1700
Data Index: 2394094 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.7848. Min Act: -0.1700
Data Index: 4833695 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 5191001 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.7536. Min Act: -0.1700
Data Index: 4006384 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.7223. Min Act: -0.1700
Data Index: 4834391 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6911. Min Act: -0.1700
Data Index: 561959 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 3511355 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6598. Min Act: -0.1700
Data Index: 4802402 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6598. Min Act: -0.1700
Data Index: 6829895 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 6933887 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 780656 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4411. Min Range: -5.4411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 5665361 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19