Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.3269. Min Act: -0.1700
Data Index: 8718377 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.3269. Min Act: -0.1700
Data Index: 1272088 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.2644. Min Act: -0.1700
Data Index: 439149 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.2332. Min Act: -0.1700
Data Index: 1964199 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.2332. Min Act: -0.1700
Data Index: 1886524 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1707. Min Act: -0.1700
Data Index: 4234936 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1707. Min Act: -0.1700
Data Index: 8718372 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1707. Min Act: -0.1700
Data Index: 2631746 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1707. Min Act: -0.1700
Data Index: 1272087 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1394. Min Act: -0.1700
Data Index: 7434662 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1394. Min Act: -0.1700
Data Index: 4374903 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1082. Min Act: -0.1700
Data Index: 5029989 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1082. Min Act: -0.1700
Data Index: 727184 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.1082. Min Act: -0.1700
Data Index: 5548032 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.0769. Min Act: -0.1700
Data Index: 6066788 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.0769. Min Act: -0.1700
Data Index: 4363415 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.0769. Min Act: -0.1700
Data Index: 3027062 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.0457. Min Act: -0.1700
Data Index: 8716014 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.0457. Min Act: -0.1700
Data Index: 8223970 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3269. Min Range: -5.3269
Max Act: 5.0457. Min Act: -0.1700
Data Index: 4795567 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19