Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4189 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1449. Min Range: -7.1449
Max Act: 7.1449. Min Act: -0.1700
Data Index: 1447105 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.9886. Min Act: -0.1700
Data Index: 3087988 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.8324. Min Act: -0.1700
Data Index: 4117411 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.8011. Min Act: -0.1700
Data Index: 3087989 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.7699. Min Act: -0.1700
Data Index: 8313396 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.8011. Min Act: -0.1700
Data Index: 5223276 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.7074. Min Act: -0.1700
Data Index: 771889 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.6761. Min Act: -0.1700
Data Index: 4122175 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.6449. Min Act: -0.1700
Data Index: 5277832 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.6449. Min Act: -0.1700
Data Index: 935760 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.5511. Min Act: -0.1700
Data Index: 814017 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.5199. Min Act: -0.1700
Data Index: 4903584 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.5199. Min Act: -0.1700
Data Index: 1184108 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.5199. Min Act: -0.1700
Data Index: 2538729 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.5199. Min Act: -0.1700
Data Index: 8341516 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.4886. Min Act: -0.1700
Data Index: 1018230 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.4886. Min Act: -0.1700
Data Index: 1983972 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7660008 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.4574. Min Act: -0.1700
Data Index: 2345973 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1449. Min Range: -7.1449
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7857320 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19