Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5188. Min Range: -6.5188
Max Act: 6.5188. Min Act: -0.1700
Data Index: 2586364 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5188. Min Range: -6.5188
Max Act: 6.1751. Min Act: -0.1700
Data Index: 3248638 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5188. Min Range: -6.5188
Max Act: 6.0813. Min Act: -0.1700
Data Index: 7790032 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5188. Min Range: -6.5188
Max Act: 6.0813. Min Act: -0.1700
Data Index: 1696479 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.9876. Min Act: -0.1700
Data Index: 5164782 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.9251. Min Act: -0.1700
Data Index: 4121360 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.9251. Min Act: -0.1700
Data Index: 8780529 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8938. Min Act: -0.1700
Data Index: 5832326 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8938. Min Act: -0.1700
Data Index: 4583985 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8313. Min Act: -0.1700
Data Index: 1895955 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8313. Min Act: -0.1700
Data Index: 5844376 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8313. Min Act: -0.1700
Data Index: 1598214 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7441388 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8626. Min Act: -0.1700
Data Index: 7122779 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.8001. Min Act: -0.1700
Data Index: 3431861 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.7688. Min Act: -0.1700
Data Index: 4839609 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8682377 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.7376. Min Act: -0.1700
Data Index: 8182722 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.7376. Min Act: -0.1700
Data Index: 3426634 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5188. Min Range: -6.5188
Max Act: 5.7688. Min Act: -0.1700
Data Index: 5599251 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19