Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.8976. Min Act: -0.1700
Data Index: 3909539 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7414. Min Act: -0.1700
Data Index: 4716257 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7414. Min Act: -0.1700
Data Index: 5536072 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7414. Min Act: -0.1700
Data Index: 389296 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7101. Min Act: -0.1700
Data Index: 88162 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7101. Min Act: -0.1700
Data Index: 5727941 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7101. Min Act: -0.1700
Data Index: 3462551 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7101. Min Act: -0.1700
Data Index: 4034973 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.7414. Min Act: -0.1700
Data Index: 3833963 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.6789. Min Act: -0.1700
Data Index: 3334355 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.6789. Min Act: -0.1700
Data Index: 7404557 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.6789. Min Act: -0.1700
Data Index: 7993742 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.6789. Min Act: -0.1700
Data Index: 1945892 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.6476. Min Act: -0.1700
Data Index: 6535716 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.6476. Min Act: -0.1700
Data Index: 6798927 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.5851. Min Act: -0.1700
Data Index: 1638811 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.5851. Min Act: -0.1700
Data Index: 1843641 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.5851. Min Act: -0.1700
Data Index: 88163 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.5851. Min Act: -0.1700
Data Index: 814656 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8976. Min Range: -4.8976
Max Act: 4.5851. Min Act: -0.1700
Data Index: 6322363 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19