Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1592 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.2500. Min Act: -0.1699
Data Index: 6036277 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.2500. Min Act: -0.1700
Data Index: 7665408 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.1875. Min Act: -0.1700
Data Index: 7588908 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.1875. Min Act: -0.1692
Data Index: 2338125 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.1875. Min Act: -0.1700
Data Index: 7934350 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.1250. Min Act: -0.1699
Data Index: 6391314 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0625. Min Act: -0.1694
Data Index: 2983039 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0625. Min Act: -0.1700
Data Index: 6191803 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0625. Min Act: -0.1700
Data Index: 1298742 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0625. Min Act: -0.1700
Data Index: 7944498 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0625. Min Act: -0.1700
Data Index: 8012798 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0625. Min Act: -0.1700
Data Index: 7750393 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0000. Min Act: -0.1700
Data Index: 4867741 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0000. Min Act: -0.1700
Data Index: 649057 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0000. Min Act: -0.1700
Data Index: 2053513 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2500. Min Range: -7.2500
Max Act: 6.9375. Min Act: -0.1700
Data Index: 4714470 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0000. Min Act: -0.1697
Data Index: 7529695 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2500. Min Range: -7.2500
Max Act: 7.0000. Min Act: -0.1700
Data Index: 5874265 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2500. Min Range: -7.2500
Max Act: 6.9375. Min Act: -0.1698
Data Index: 568204 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2500. Min Range: -7.2500
Max Act: 6.9375. Min Act: -0.1700
Data Index: 6471110 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19