Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0445. Min Range: -7.0445
Max Act: 7.0445. Min Act: -0.1700
Data Index: 8251893 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.9507. Min Act: -0.1700
Data Index: 5592671 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.9195. Min Act: -0.1700
Data Index: 92629 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.9195. Min Act: -0.1700
Data Index: 6570609 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.8882. Min Act: -0.1700
Data Index: 737461 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.8257. Min Act: -0.1700
Data Index: 8198367 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.7320. Min Act: -0.1700
Data Index: 5581007 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.7320. Min Act: -0.1700
Data Index: 5099003 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.7007. Min Act: -0.1700
Data Index: 1918050 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.6695. Min Act: -0.1700
Data Index: 3357692 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.6695. Min Act: -0.1700
Data Index: 2570211 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.6695. Min Act: -0.1700
Data Index: 8529227 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.6382. Min Act: -0.1699
Data Index: 3793635 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.6382. Min Act: -0.1700
Data Index: 5322846 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.6070. Min Act: -0.1700
Data Index: 2574141 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.5757. Min Act: -0.1700
Data Index: 1549143 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.5757. Min Act: -0.1700
Data Index: 5432583 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.5757. Min Act: -0.1700
Data Index: 581526 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.5445. Min Act: -0.1700
Data Index: 1094874 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0445. Min Range: -7.0445
Max Act: 6.5445. Min Act: -0.1700
Data Index: 4208916 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19