Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.8159. Min Act: -0.1700
Data Index: 2915642 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7690. Min Act: -0.1700
Data Index: 3691997 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7690. Min Act: -0.1700
Data Index: 3810466 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7533. Min Act: -0.1700
Data Index: 3927515 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7533. Min Act: -0.1700
Data Index: 7564164 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7377. Min Act: -0.1700
Data Index: 8728700 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7221. Min Act: -0.1700
Data Index: 51891 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6908. Min Act: -0.1700
Data Index: 8682684 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.7064. Min Act: -0.1700
Data Index: 6018077 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6751. Min Act: -0.1700
Data Index: 2471590 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6751. Min Act: -0.1700
Data Index: 6430387 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6751. Min Act: -0.1700
Data Index: 3271528 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6751. Min Act: -0.1700
Data Index: 5412521 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6438. Min Act: -0.1700
Data Index: 4549132 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6595. Min Act: -0.1700
Data Index: 6454375 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6125. Min Act: -0.1700
Data Index: 5582889 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6282. Min Act: -0.1700
Data Index: 3348600 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6282. Min Act: -0.1700
Data Index: 3170792 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.5969. Min Act: -0.1700
Data Index: 5500384 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8159. Min Range: -3.8159
Max Act: 3.6125. Min Act: -0.1700
Data Index: 1936657 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19