Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0813. Min Range: -6.0813
Max Act: 6.0813. Min Act: -0.1700
Data Index: 3708928 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.9251. Min Act: -0.1700
Data Index: 2677961 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.8938. Min Act: -0.1700
Data Index: 4020392 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.8938. Min Act: -0.1700
Data Index: 287043 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.8001. Min Act: -0.1700
Data Index: 4621816 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6023529 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.6751. Min Act: -0.1700
Data Index: 4208285 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.6126. Min Act: -0.1700
Data Index: 4554973 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.6126. Min Act: -0.1700
Data Index: 887931 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.5813. Min Act: -0.1700
Data Index: 7291667 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.5501. Min Act: -0.1700
Data Index: 5501279 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.5501. Min Act: -0.1700
Data Index: 1916313 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.5188. Min Act: -0.1700
Data Index: 2975492 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.5813. Min Act: -0.1700
Data Index: 7342508 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.5188. Min Act: -0.1700
Data Index: 2837057 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.4876. Min Act: -0.1700
Data Index: 2267700 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.4563. Min Act: -0.1700
Data Index: 5600709 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 1449303 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4921454 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0813. Min Range: -6.0813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 3976721 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19