Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4680 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.7361. Min Act: -0.1700
Data Index: 8439289 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.6736. Min Act: -0.1700
Data Index: 4627258 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.5486. Min Act: -0.1700
Data Index: 140156 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.5486. Min Act: -0.1700
Data Index: 809278 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.4861. Min Act: -0.1700
Data Index: 4973165 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.3611. Min Act: -0.1700
Data Index: 5154945 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.3611. Min Act: -0.1700
Data Index: 3750689 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.3611. Min Act: -0.1700
Data Index: 3387767 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.2986. Min Act: -0.1700
Data Index: 5076940 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.2361. Min Act: -0.1700
Data Index: 4196 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.2361. Min Act: -0.1700
Data Index: 3334647 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.2361. Min Act: -0.1700
Data Index: 1411678 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.2361. Min Act: -0.1700
Data Index: 8008732 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.1111. Min Act: -0.1700
Data Index: 8831594 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.1736. Min Act: -0.1700
Data Index: 7259586 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.1111. Min Act: -0.1700
Data Index: 3977295 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.1111. Min Act: -0.1700
Data Index: 3802085 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.1111. Min Act: -0.1700
Data Index: 7528695 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.0486. Min Act: -0.1700
Data Index: 4525888 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7361. Min Range: -8.7361
Max Act: 8.0486. Min Act: -0.1700
Data Index: 2311587 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19