Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6354 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1914. Min Range: -8.1914
Max Act: 8.1914. Min Act: -0.1700
Data Index: 629224 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1914. Min Range: -8.1914
Max Act: 8.0664. Min Act: -0.1700
Data Index: 7567498 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.9414. Min Act: -0.1700
Data Index: 2328380 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.8789. Min Act: -0.1700
Data Index: 4891373 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.8789. Min Act: -0.1700
Data Index: 6848732 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.8164. Min Act: -0.1700
Data Index: 6819968 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.8164. Min Act: -0.1700
Data Index: 1530386 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.8164. Min Act: -0.1700
Data Index: 8269737 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.7539. Min Act: -0.1700
Data Index: 7899833 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6914. Min Act: -0.1700
Data Index: 3162573 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.7539. Min Act: -0.1700
Data Index: 8387131 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.7539. Min Act: -0.1700
Data Index: 6439341 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.7539. Min Act: -0.1700
Data Index: 7472075 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.8164. Min Act: -0.1700
Data Index: 5376856 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6914. Min Act: -0.1700
Data Index: 6640498 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6914. Min Act: -0.1700
Data Index: 7284194 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6914. Min Act: -0.1700
Data Index: 7429086 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6289. Min Act: -0.1700
Data Index: 1285991 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6289. Min Act: -0.1700
Data Index: 5810643 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1914. Min Range: -8.1914
Max Act: 7.6289. Min Act: -0.1700
Data Index: 4494267 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19