Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 873 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0304. Min Act: -0.0000

Data Index: 735134 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1010985 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1089676 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0289. Min Act: -0.0000

Data Index: 174602 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0264. Min Act: -0.0000

Data Index: 908197 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0274. Min Act: -0.0000

Data Index: 164632 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0278. Min Act: -0.0000

Data Index: 525096 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0248. Min Act: -0.0000

Data Index: 536050 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0216. Min Act: -0.0000

Data Index: 654803 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0255. Min Act: -0.0000

Data Index: 605283 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0263. Min Act: -0.0000

Data Index: 660561 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1146981 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1339862 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0229. Min Act: -0.0000

Data Index: 365489 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1653184 (Python Code)

Max Activating Token Index: 834

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0201. Min Act: -0.0000

Data Index: 804992 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0220. Min Act: -0.0000

Data Index: 1057189 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0222. Min Act: -0.0000

Data Index: 435063 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0214. Min Act: -0.0000

Data Index: 472359 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0222. Min Act: -0.0000

Data Index: 218800 (C4 (Web Text))

Max Activating Token Index: 62