Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.7431. Min Act: -0.1700
Data Index: 1980370 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.6806. Min Act: -0.1700
Data Index: 8632499 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.6806. Min Act: -0.1700
Data Index: 597091 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.5869. Min Act: -0.1700
Data Index: 4362513 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.5869. Min Act: -0.1700
Data Index: 5029887 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 845038 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 5467788 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.5244. Min Act: -0.1700
Data Index: 5954268 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.4306. Min Act: -0.1700
Data Index: 5058344 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3994. Min Act: -0.1700
Data Index: 2554026 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3681. Min Act: -0.1700
Data Index: 1189256 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3994. Min Act: -0.1700
Data Index: 5517791 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.4306. Min Act: -0.1700
Data Index: 6531721 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3681. Min Act: -0.1700
Data Index: 2905509 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3369. Min Act: -0.1700
Data Index: 2107733 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3056. Min Act: -0.1700
Data Index: 5114484 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3056. Min Act: -0.1700
Data Index: 192210 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3056. Min Act: -0.1700
Data Index: 2489567 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3056. Min Act: -0.1700
Data Index: 2496628 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7431. Min Range: -5.7431
Max Act: 5.3056. Min Act: -0.1700
Data Index: 3527007 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19