Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 731 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.7906. Min Act: -0.1700
Data Index: 7833580 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.7281. Min Act: -0.1700
Data Index: 691235 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.6344. Min Act: -0.1700
Data Index: 2428865 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.6031. Min Act: -0.1700
Data Index: 906692 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.5406. Min Act: -0.1700
Data Index: 7833581 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.5406. Min Act: -0.1700
Data Index: 1698046 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.5094. Min Act: -0.1700
Data Index: 1562271 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4781. Min Act: -0.1700
Data Index: 1698045 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4469. Min Act: -0.1700
Data Index: 1979495 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 4828479 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 4037738 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 7969427 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 4037736 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 691234 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 7188019 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.4156. Min Act: -0.1700
Data Index: 3953622 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.3844. Min Act: -0.1700
Data Index: 5888485 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.3844. Min Act: -0.1700
Data Index: 1544193 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.3844. Min Act: -0.1700
Data Index: 6408758 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7906. Min Range: -5.7906
Max Act: 5.3844. Min Act: -0.1699
Data Index: 7521041 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19