Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.9978. Min Range: -12.9978
Max Act: 12.9978. Min Act: -0.1700
Data Index: 111219 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.8728. Min Act: -0.1700
Data Index: 5143137 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.8103. Min Act: -0.1700
Data Index: 581370 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.6853. Min Act: -0.1700
Data Index: 1403848 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.6228. Min Act: -0.1700
Data Index: 1111732 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.4353. Min Act: -0.1700
Data Index: 3019797 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.3728. Min Act: -0.1700
Data Index: 7926578 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.3103. Min Act: -0.1700
Data Index: 2882045 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.1853. Min Act: -0.1700
Data Index: 5937606 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.9978. Min Act: -0.1700
Data Index: 979682 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.9978. Min Act: -0.1700
Data Index: 1661013 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.9353. Min Act: -0.1700
Data Index: 5248195 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9978. Min Range: -12.9978
Max Act: 11.0603. Min Act: -0.1700
Data Index: 3348677 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.9978. Min Act: -0.1700
Data Index: 5952110 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.8728. Min Act: -0.1700
Data Index: 4477733 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.8103. Min Act: -0.1700
Data Index: 6077427 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.6853. Min Act: -0.1700
Data Index: 7400171 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.6853. Min Act: -0.1700
Data Index: 7853803 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.6853. Min Act: -0.1700
Data Index: 472880 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9978. Min Range: -12.9978
Max Act: 10.6228. Min Act: -0.1700
Data Index: 5361234 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19