Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.3848. Min Act: -0.1700
Data Index: 8349793 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.2203. Min Act: -0.1700
Data Index: 4364313 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.2037. Min Act: -0.1700
Data Index: 4364311 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.2037. Min Act: -0.1700
Data Index: 1472991 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.2037. Min Act: -0.1700
Data Index: 660714 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1705. Min Act: -0.1700
Data Index: 4662624 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1871. Min Act: -0.1700
Data Index: 3780950 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1539. Min Act: -0.1700
Data Index: 8153622 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 8203352 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 7352889 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 3702433 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 1650052 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 8227828 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 5958306 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 1032692 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1372. Min Act: -0.1700
Data Index: 8587586 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1205. Min Act: -0.1700
Data Index: 3485311 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1205. Min Act: -0.1700
Data Index: 629985 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1205. Min Act: -0.1700
Data Index: 4364310 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3848. Min Range: -2.3848
Max Act: 2.1038. Min Act: -0.1700
Data Index: 5315001 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19