Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2882. Min Range: -6.2882
Max Act: 6.2882. Min Act: -0.1700
Data Index: 5172754 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2882. Min Range: -6.2882
Max Act: 6.0695. Min Act: -0.1700
Data Index: 6731268 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2882. Min Range: -6.2882
Max Act: 6.0695. Min Act: -0.1700
Data Index: 1870599 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2882. Min Range: -6.2882
Max Act: 6.0382. Min Act: -0.1700
Data Index: 2265824 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.9757. Min Act: -0.1700
Data Index: 5563675 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.9757. Min Act: -0.1700
Data Index: 1589244 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.9757. Min Act: -0.1700
Data Index: 8696393 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.9757. Min Act: -0.1700
Data Index: 3428347 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.9757. Min Act: -0.1700
Data Index: 8153714 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.9132. Min Act: -0.1700
Data Index: 6603461 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8820. Min Act: -0.1700
Data Index: 7093722 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8820. Min Act: -0.1700
Data Index: 4466436 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8820. Min Act: -0.1700
Data Index: 8634607 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8507. Min Act: -0.1700
Data Index: 6553484 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8507. Min Act: -0.1700
Data Index: 247534 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8507. Min Act: -0.1700
Data Index: 8790730 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8195. Min Act: -0.1700
Data Index: 1058294 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8195. Min Act: -0.1700
Data Index: 4829769 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8195. Min Act: -0.1700
Data Index: 5306375 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2882. Min Range: -6.2882
Max Act: 5.8195. Min Act: -0.1700
Data Index: 6075653 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19