Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4885 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.4188. Min Act: -0.1700
Data Index: 8722699 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.2313. Min Act: -0.1700
Data Index: 3478151 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.1063. Min Act: -0.1700
Data Index: 4345733 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.1063. Min Act: -0.1700
Data Index: 6337835 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.1063. Min Act: -0.1700
Data Index: 218222 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.0438. Min Act: -0.1700
Data Index: 8045843 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4188. Min Range: -8.4188
Max Act: 8.0438. Min Act: -0.1700
Data Index: 3222433 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.9813. Min Act: -0.1700
Data Index: 7248107 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.8563. Min Act: -0.1700
Data Index: 7587628 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.9188. Min Act: -0.1700
Data Index: 8155186 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.9188. Min Act: -0.1700
Data Index: 3506019 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.8563. Min Act: -0.1700
Data Index: 352775 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.9188. Min Act: -0.1700
Data Index: 7627657 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.8563. Min Act: -0.1700
Data Index: 6169957 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.8563. Min Act: -0.1700
Data Index: 4948054 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.7938. Min Act: -0.1700
Data Index: 1007121 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.7938. Min Act: -0.1700
Data Index: 1168343 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.7938. Min Act: -0.1700
Data Index: 6374091 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.7938. Min Act: -0.1700
Data Index: 6714805 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4188. Min Range: -8.4188
Max Act: 7.7938. Min Act: -0.1700
Data Index: 8579537 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19