Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5570 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1357. Min Range: -7.1357
Max Act: 7.1357. Min Act: -0.1700
Data Index: 5122734 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.6669. Min Act: -0.1700
Data Index: 4650371 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.6669. Min Act: -0.1700
Data Index: 5482729 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.6044. Min Act: -0.1700
Data Index: 1938920 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.5107. Min Act: -0.1700
Data Index: 3647470 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.4169. Min Act: -0.1700
Data Index: 5314018 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.3232. Min Act: -0.1700
Data Index: 968633 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.2919. Min Act: -0.1700
Data Index: 3319646 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.1982. Min Act: -0.1700
Data Index: 2690475 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.1357. Min Act: -0.1700
Data Index: 8534849 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.1044. Min Act: -0.1700
Data Index: 539829 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.0732. Min Act: -0.1700
Data Index: 2331561 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.0419. Min Act: -0.1700
Data Index: 2091772 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.0419. Min Act: -0.1700
Data Index: 1340459 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.0107. Min Act: -0.1700
Data Index: 3446253 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1357. Min Range: -7.1357
Max Act: 6.0107. Min Act: -0.1700
Data Index: 2524285 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1357. Min Range: -7.1357
Max Act: 5.9794. Min Act: -0.1700
Data Index: 7182492 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1357. Min Range: -7.1357
Max Act: 5.9482. Min Act: -0.1700
Data Index: 630442 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1357. Min Range: -7.1357
Max Act: 5.9482. Min Act: -0.1700
Data Index: 2074598 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1357. Min Range: -7.1357
Max Act: 5.9482. Min Act: -0.1700
Data Index: 342445 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19