Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5102. Min Range: -11.5102
Max Act: 11.5102. Min Act: -0.1700
Data Index: 4007401 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5102. Min Range: -11.5102
Max Act: 11.1977. Min Act: -0.1700
Data Index: 4447407 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5102. Min Range: -11.5102
Max Act: 11.1977. Min Act: -0.1700
Data Index: 992564 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5102. Min Range: -11.5102
Max Act: 11.0102. Min Act: -0.1700
Data Index: 6144483 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.9477. Min Act: -0.1700
Data Index: 1627009 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.9477. Min Act: -0.1700
Data Index: 3727226 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.9477. Min Act: -0.1700
Data Index: 3241428 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.8852. Min Act: -0.1700
Data Index: 3906285 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.8852. Min Act: -0.1700
Data Index: 2744022 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.8227. Min Act: -0.1700
Data Index: 5720395 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.8227. Min Act: -0.1700
Data Index: 4265172 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.8227. Min Act: -0.1700
Data Index: 5842919 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 12984 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 5681121 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 2690616 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 4096235 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 1358831 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 2256706 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 3075564 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5102. Min Range: -11.5102
Max Act: 10.7602. Min Act: -0.1700
Data Index: 4775744 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19