Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2715 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.6431. Min Act: -0.1700
Data Index: 1981913 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.6431. Min Act: -0.1700
Data Index: 5199321 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.5181. Min Act: -0.1700
Data Index: 1981908 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.3931. Min Act: -0.1700
Data Index: 4562926 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.3931. Min Act: -0.1700
Data Index: 4562927 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 4669032 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 4562916 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 4669021 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.2681. Min Act: -0.1700
Data Index: 6099322 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 6099330 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 3782971 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 4669034 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 8719932 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.1431. Min Act: -0.1700
Data Index: 6099329 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.1431. Min Act: -0.1700
Data Index: 6099324 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.1431. Min Act: -0.1700
Data Index: 3566011 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.0806. Min Act: -0.1700
Data Index: 6099318 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.1431. Min Act: -0.1700
Data Index: 8778899 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6431. Min Range: -9.6431
Max Act: 9.0181. Min Act: -0.1700
Data Index: 8778898 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6431. Min Range: -9.6431
Max Act: 8.9556. Min Act: -0.1700
Data Index: 1981916 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19