Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.7697. Min Act: -0.1700
Data Index: 8537900 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.5510. Min Act: -0.1700
Data Index: 3772378 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.2385. Min Act: -0.1700
Data Index: 668933 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.1447. Min Act: -0.1700
Data Index: 3337911 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.1447. Min Act: -0.1700
Data Index: 3600514 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.1135. Min Act: -0.1700
Data Index: 4683309 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0510. Min Act: -0.1700
Data Index: 6622596 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0197. Min Act: -0.1700
Data Index: 1158536 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0197. Min Act: -0.1700
Data Index: 6288519 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0510. Min Act: -0.1700
Data Index: 5854645 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0197. Min Act: -0.1700
Data Index: 850044 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0197. Min Act: -0.1700
Data Index: 6742252 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7697. Min Range: -6.7697
Max Act: 6.0197. Min Act: -0.1700
Data Index: 1905483 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 339090 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6552433 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6286725 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9260. Min Act: -0.1700
Data Index: 7972095 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9885. Min Act: -0.1700
Data Index: 1013440 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 7116557 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7697. Min Range: -6.7697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 3504646 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19