Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4917 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9843. Min Act: -0.0000

Data Index: 31622 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9991. Min Act: -0.0000

Data Index: 50995 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1038227 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8828. Min Act: -0.0000

Data Index: 671885 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8746. Min Act: -0.0000

Data Index: 736785 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1046534 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1324490 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8280. Min Act: -0.0000

Data Index: 278982 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1288160 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8568. Min Act: -0.0000

Data Index: 643280 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8456. Min Act: -0.0000

Data Index: 731875 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8108. Min Act: -0.0000

Data Index: 987166 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1240855 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1229913 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1260591 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7752. Min Act: -0.0000

Data Index: 803918 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1315631 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1326822 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7441. Min Act: -0.0000

Data Index: 627854 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8010. Min Act: -0.0000

Data Index: 123949 (C4 (Web Text))

Max Activating Token Index: 557