Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5252 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1579. Min Range: -7.1579
Max Act: 7.1579. Min Act: -0.1700
Data Index: 6589094 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.6579. Min Act: -0.1700
Data Index: 6164628 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.5954. Min Act: -0.1700
Data Index: 6463894 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.5954. Min Act: -0.1700
Data Index: 8403924 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.5329. Min Act: -0.1700
Data Index: 3478187 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.5017. Min Act: -0.1700
Data Index: 1510529 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.4392. Min Act: -0.1700
Data Index: 3141080 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.3767. Min Act: -0.1700
Data Index: 7239857 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.3767. Min Act: -0.1700
Data Index: 277502 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 2250779 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 5274355 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 8743067 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 6945659 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 6721883 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 1773051 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 1070122 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 2422797 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 8478210 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 4961804 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1579. Min Range: -7.1579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 6224840 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19