Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4755 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0886. Min Range: -7.0886
Max Act: 7.0886. Min Act: -0.1700
Data Index: 674234 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.9323. Min Act: -0.1700
Data Index: 3031725 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.5573. Min Act: -0.1700
Data Index: 8554533 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.4323. Min Act: -0.1700
Data Index: 4665305 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.4011. Min Act: -0.1700
Data Index: 4175751 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3698. Min Act: -0.1700
Data Index: 4053632 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3698. Min Act: -0.1700
Data Index: 4665307 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3698. Min Act: -0.1700
Data Index: 1564001 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3698. Min Act: -0.1700
Data Index: 4107594 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3386. Min Act: -0.1700
Data Index: 1333266 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3386. Min Act: -0.1700
Data Index: 8392054 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3073. Min Act: -0.1700
Data Index: 454157 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2761. Min Act: -0.1700
Data Index: 7459550 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3386. Min Act: -0.1700
Data Index: 721264 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2761. Min Act: -0.1700
Data Index: 6474645 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2761. Min Act: -0.1700
Data Index: 6630446 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2761. Min Act: -0.1700
Data Index: 4256833 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2136. Min Act: -0.1700
Data Index: 6526044 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2136. Min Act: -0.1700
Data Index: 4014219 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2136. Min Act: -0.1700
Data Index: 1718530 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19