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

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

Neuron 249 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: 0.0306. Min Range: -0.0306

Max Act: 0.0252. Min Act: -0.0002

Data Index: 926952 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0002

Data Index: 821480 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0248. Min Act: -0.0002

Data Index: 730788 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1183021 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0252. Min Act: -0.0002

Data Index: 691158 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0210. Min Act: -0.0002

Data Index: 241315 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0218. Min Act: -0.0002

Data Index: 160362 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1096692 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0206. Min Act: -0.0002

Data Index: 497392 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0204. Min Act: -0.0002

Data Index: 206711 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0175. Min Act: -0.0002

Data Index: 824687 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0222. Min Act: -0.0002

Data Index: 345129 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0203. Min Act: -0.0002

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1272574 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1454070 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1229 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0199. Min Act: -0.0002

Data Index: 186929 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1349387 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1271244 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1202973 (C4 (Web Text))

Max Activating Token Index: 952