Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.8916. Min Act: -0.1700
Data Index: 8534211 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.5166. Min Act: -0.1700
Data Index: 6321989 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3916. Min Act: -0.1700
Data Index: 2852510 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3916. Min Act: -0.1700
Data Index: 6426698 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3603. Min Act: -0.1700
Data Index: 6161287 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2666. Min Act: -0.1700
Data Index: 5947920 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 781999 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2666. Min Act: -0.1700
Data Index: 2816790 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2666. Min Act: -0.1700
Data Index: 762730 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2666. Min Act: -0.1700
Data Index: 1702430 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2353. Min Act: -0.1700
Data Index: 8364986 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2353. Min Act: -0.1700
Data Index: 3846894 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2353. Min Act: -0.1700
Data Index: 1639940 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1728. Min Act: -0.1700
Data Index: 4208247 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1103. Min Act: -0.1700
Data Index: 1622146 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1416. Min Act: -0.1700
Data Index: 5833094 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1416. Min Act: -0.1700
Data Index: 8036882 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1416. Min Act: -0.1700
Data Index: 5146512 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1103. Min Act: -0.1700
Data Index: 616619 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.1103. Min Act: -0.1700
Data Index: 445527 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19