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

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

Neuron 3100 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.5281. Min Act: -0.0000

Data Index: 1068356 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1288795 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.2204. Min Act: -0.0000

Data Index: 647644 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.1957. Min Act: -0.0000

Data Index: 1170005 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1078059 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.0859. Min Act: -0.0000

Data Index: 848012 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.1222. Min Act: -0.0000

Data Index: 645066 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.1151. Min Act: -0.0000

Data Index: 914467 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.1813. Min Act: -0.0000

Data Index: 18539 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.0684. Min Act: -0.0000

Data Index: 465306 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.0577. Min Act: -0.0000

Data Index: 970674 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1607388 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1074671 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.5281. Min Range: -1.5281

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1547875 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 1.5281. Min Range: -1.5281

Max Act: 1.0215. Min Act: -0.0000

Data Index: 713260 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.5281. Min Range: -1.5281

Max Act: 0.8394. Min Act: -0.0000

Data Index: 761918 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.5281. Min Range: -1.5281

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1286071 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.5281. Min Range: -1.5281

Max Act: 0.8317. Min Act: -0.0000

Data Index: 520585 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.5281. Min Range: -1.5281

Max Act: 0.8151. Min Act: -0.0000

Data Index: 615784 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.5281. Min Range: -1.5281

Max Act: 0.8572. Min Act: -0.0000

Data Index: 495582 (C4 (Web Text))

Max Activating Token Index: 973