Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.5938. Min Act: -0.1700
Data Index: 2584610 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.4063. Min Act: -0.1700
Data Index: 4306348 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.2501. Min Act: -0.1700
Data Index: 3406143 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.1563. Min Act: -0.1700
Data Index: 4881718 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.0313. Min Act: -0.1700
Data Index: 6674500 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.0313. Min Act: -0.1700
Data Index: 2266795 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.0001. Min Act: -0.1700
Data Index: 3772343 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5938. Min Range: -7.5938
Max Act: 7.0001. Min Act: -0.1700
Data Index: 7731890 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.9688. Min Act: -0.1700
Data Index: 3937950 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.9063. Min Act: -0.1700
Data Index: 6999611 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.8438. Min Act: -0.1700
Data Index: 7391512 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.8751. Min Act: -0.1700
Data Index: 1319597 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.8438. Min Act: -0.1700
Data Index: 5984333 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.8438. Min Act: -0.1700
Data Index: 1874520 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.7813. Min Act: -0.1700
Data Index: 8485338 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.8126. Min Act: -0.1700
Data Index: 8822016 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.7813. Min Act: -0.1700
Data Index: 6252008 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.7501. Min Act: -0.1700
Data Index: 5971136 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.7813. Min Act: -0.1700
Data Index: 3563226 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5938. Min Range: -7.5938
Max Act: 6.7813. Min Act: -0.1700
Data Index: 743941 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19