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

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

Neuron 44 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0002

Data Index: 763210 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0252. Min Act: -0.0002

Data Index: 589202 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0002

Data Index: 212003 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0199. Min Act: -0.0002

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1067481 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0178. Min Act: -0.0002

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0204. Min Act: -0.0002

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0217. Min Act: -0.0002

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0204. Min Act: -0.0002

Data Index: 869089 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1130330 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0219. Min Act: -0.0002

Data Index: 398573 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1157262 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0176. Min Act: -0.0002

Data Index: 126679 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1626721 (Python Code)

Max Activating Token Index: 546

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0194. Min Act: -0.0002

Data Index: 166454 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1065279 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0171. Min Act: -0.0002

Data Index: 20102 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0189. Min Act: -0.0002

Data Index: 8362 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0187. Min Act: -0.0003

Data Index: 619865 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0186. Min Act: -0.0002

Data Index: 510141 (C4 (Web Text))

Max Activating Token Index: 381