Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1225. Min Range: -9.1225
Max Act: 9.1225. Min Act: -0.1700
Data Index: 3903978 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.8725. Min Act: -0.1700
Data Index: 8500721 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.7475. Min Act: -0.1700
Data Index: 4961948 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.7475. Min Act: -0.1700
Data Index: 3107164 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.6850. Min Act: -0.1700
Data Index: 3569110 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.6850. Min Act: -0.1700
Data Index: 4843610 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.6225. Min Act: -0.1700
Data Index: 5271185 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.6225. Min Act: -0.1700
Data Index: 1131063 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.6225. Min Act: -0.1700
Data Index: 24904 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.5600. Min Act: -0.1700
Data Index: 7360795 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.5600. Min Act: -0.1700
Data Index: 7630295 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4975. Min Act: -0.1700
Data Index: 2366164 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4975. Min Act: -0.1700
Data Index: 6413925 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4975. Min Act: -0.1700
Data Index: 1664121 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4975. Min Act: -0.1700
Data Index: 1003896 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4350. Min Act: -0.1700
Data Index: 4328242 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4350. Min Act: -0.1700
Data Index: 7630294 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4350. Min Act: -0.1700
Data Index: 1872080 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4350. Min Act: -0.1700
Data Index: 1803764 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1225. Min Range: -9.1225
Max Act: 8.4350. Min Act: -0.1700
Data Index: 427139 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19