Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2307 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.9902. Min Act: -0.1700
Data Index: 1836065 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.9277. Min Act: -0.1700
Data Index: 960773 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.8652. Min Act: -0.1700
Data Index: 6770477 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.7402. Min Act: -0.1700
Data Index: 7765217 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.7089. Min Act: -0.1700
Data Index: 5853681 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.7089. Min Act: -0.1700
Data Index: 4979994 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.7089. Min Act: -0.1700
Data Index: 2033730 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.6464. Min Act: -0.1700
Data Index: 6770476 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.6152. Min Act: -0.1700
Data Index: 7122906 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.6152. Min Act: -0.1700
Data Index: 7374396 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.6152. Min Act: -0.1700
Data Index: 3685032 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.6152. Min Act: -0.1700
Data Index: 8737322 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.5839. Min Act: -0.1700
Data Index: 11407 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.5527. Min Act: -0.1699
Data Index: 2112409 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.5527. Min Act: -0.1700
Data Index: 1042976 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.5214. Min Act: -0.1700
Data Index: 5091984 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.5214. Min Act: -0.1700
Data Index: 8486347 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.5214. Min Act: -0.1700
Data Index: 8129764 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.4902. Min Act: -0.1700
Data Index: 4486920 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9902. Min Range: -6.9902
Max Act: 6.4902. Min Act: -0.1700
Data Index: 161834 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19