Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4432 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1977. Min Range: -7.1977
Max Act: 7.1977. Min Act: -0.1700
Data Index: 4610826 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1977. Min Range: -7.1977
Max Act: 7.1352. Min Act: -0.1700
Data Index: 2106418 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.9477. Min Act: -0.1700
Data Index: 2739804 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.8852. Min Act: -0.1700
Data Index: 1916534 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.7915. Min Act: -0.1700
Data Index: 5562868 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.7602. Min Act: -0.1700
Data Index: 8080592 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.7602. Min Act: -0.1700
Data Index: 7986324 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.7602. Min Act: -0.1700
Data Index: 258896 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.7290. Min Act: -0.1700
Data Index: 1380743 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6977. Min Act: -0.1700
Data Index: 7103847 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6665. Min Act: -0.1700
Data Index: 4487556 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6665. Min Act: -0.1700
Data Index: 5606361 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6352. Min Act: -0.1700
Data Index: 8405292 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6352. Min Act: -0.1700
Data Index: 4350054 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6352. Min Act: -0.1700
Data Index: 5521891 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.5727. Min Act: -0.1700
Data Index: 3957480 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.6040. Min Act: -0.1700
Data Index: 8317228 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.5415. Min Act: -0.1700
Data Index: 1825003 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.5727. Min Act: -0.1700
Data Index: 7834302 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1977. Min Range: -7.1977
Max Act: 6.5727. Min Act: -0.1700
Data Index: 5974063 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19