Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2585478 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.7582. Min Act: -0.1700
Data Index: 2427133 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.7582. Min Act: -0.1700
Data Index: 6988596 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6957. Min Act: -0.1700
Data Index: 2472793 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.7270. Min Act: -0.1700
Data Index: 910665 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6957. Min Act: -0.1700
Data Index: 359864 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6957. Min Act: -0.1700
Data Index: 6467836 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6957. Min Act: -0.1700
Data Index: 4018851 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6645. Min Act: -0.1700
Data Index: 264292 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6645. Min Act: -0.1700
Data Index: 3955913 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6332. Min Act: -0.1700
Data Index: 7030486 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6020. Min Act: -0.1700
Data Index: 6997262 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.6332. Min Act: -0.1700
Data Index: 5000789 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.5707. Min Act: -0.1700
Data Index: 1594645 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.5707. Min Act: -0.1700
Data Index: 6142986 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.5707. Min Act: -0.1700
Data Index: 6466439 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.5395. Min Act: -0.1700
Data Index: 1334975 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.5395. Min Act: -0.1700
Data Index: 4999168 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.5082. Min Act: -0.1700
Data Index: 1308933 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8207. Min Range: -5.8207
Max Act: 5.4770. Min Act: -0.1700
Data Index: 5967759 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19