Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.7172. Min Act: -0.1700
Data Index: 2892254 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.2172. Min Act: -0.1700
Data Index: 2242607 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.1235. Min Act: -0.1700
Data Index: 3189647 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.1235. Min Act: -0.1700
Data Index: 666641 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0922. Min Act: -0.1700
Data Index: 1821632 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0922. Min Act: -0.1700
Data Index: 7396724 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0922. Min Act: -0.1700
Data Index: 4169126 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0922. Min Act: -0.1700
Data Index: 7668996 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0610. Min Act: -0.1700
Data Index: 3422980 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0610. Min Act: -0.1700
Data Index: 8621921 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7172. Min Range: -7.7172
Max Act: 7.0297. Min Act: -0.1700
Data Index: 814442 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.9985. Min Act: -0.1700
Data Index: 1976860 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.9985. Min Act: -0.1700
Data Index: 6521140 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.9985. Min Act: -0.1700
Data Index: 2688339 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.9360. Min Act: -0.1700
Data Index: 454000 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.9360. Min Act: -0.1700
Data Index: 5361971 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.9047. Min Act: -0.1700
Data Index: 7675919 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.8735. Min Act: -0.1700
Data Index: 266515 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.8735. Min Act: -0.1700
Data Index: 8427241 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7172. Min Range: -7.7172
Max Act: 6.8735. Min Act: -0.1700
Data Index: 7432016 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19