Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9375. Min Act: -0.1700
Data Index: 4834986 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8750. Min Act: -0.1700
Data Index: 6133384 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9062. Min Act: -0.1700
Data Index: 1487444 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8750. Min Act: -0.1700
Data Index: 2687393 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8437. Min Act: -0.1700
Data Index: 6034605 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8124. Min Act: -0.1700
Data Index: 6875017 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 6758803 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 402628 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8124. Min Act: -0.1700
Data Index: 1835682 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8124. Min Act: -0.1700
Data Index: 6034604 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8437. Min Act: -0.1700
Data Index: 8148477 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8124. Min Act: -0.1700
Data Index: 7808349 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8124. Min Act: -0.1700
Data Index: 7707432 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7499. Min Act: -0.1700
Data Index: 4566422 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 6034593 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 1487434 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1699
Data Index: 6034603 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1697
Data Index: 6034598 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7499. Min Act: -0.1700
Data Index: 1056705 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7186. Min Act: -0.1700
Data Index: 1313467 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19