Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1697
Data Index: 8428835 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1691
Data Index: 7405197 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 5730721 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 4139101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 8256400 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1693
Data Index: 7926747 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1697
Data Index: 1437229 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 3561295 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 2788659 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 3821294 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.9848. Min Act: -0.1700
Data Index: 4639416 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.7348. Min Act: -0.1698
Data Index: 6424746 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.7348. Min Act: -0.1700
Data Index: 6155537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.7348. Min Act: -0.1700
Data Index: 6077971 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.7348. Min Act: -0.1700
Data Index: 5817202 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.6723. Min Act: -0.1700
Data Index: 6769506 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.6098. Min Act: -0.1700
Data Index: 8063825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.4848. Min Act: -0.1700
Data Index: 3340879 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.4848. Min Act: -0.1700
Data Index: 281627 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9848. Min Range: -10.9848
Max Act: 10.4848. Min Act: -0.1700
Data Index: 3349910 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19