Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2826. Min Range: -8.2826
Max Act: 8.2826. Min Act: -0.1700
Data Index: 4682993 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2826. Min Range: -8.2826
Max Act: 8.0638. Min Act: -0.1700
Data Index: 2032750 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.9701. Min Act: -0.1700
Data Index: 6466733 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.8763. Min Act: -0.1700
Data Index: 3487973 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.7513. Min Act: -0.1700
Data Index: 3947336 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.7513. Min Act: -0.1700
Data Index: 3893829 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.6576. Min Act: -0.1700
Data Index: 7848709 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.6263. Min Act: -0.1700
Data Index: 4771662 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.6263. Min Act: -0.1700
Data Index: 7545395 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.5951. Min Act: -0.1700
Data Index: 8231801 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.5326. Min Act: -0.1700
Data Index: 5474904 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.5638. Min Act: -0.1700
Data Index: 2885240 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.5326. Min Act: -0.1700
Data Index: 884208 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.5013. Min Act: -0.1700
Data Index: 4004710 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.5013. Min Act: -0.1700
Data Index: 4441369 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.4076. Min Act: -0.1700
Data Index: 6775020 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.3763. Min Act: -0.1700
Data Index: 5473314 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.4076. Min Act: -0.1700
Data Index: 7759025 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.3763. Min Act: -0.1700
Data Index: 1628511 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2826. Min Range: -8.2826
Max Act: 7.4076. Min Act: -0.1700
Data Index: 807354 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19