Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2494 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0224. Min Act: -0.0001

Data Index: 823727 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0226. Min Act: -0.0001

Data Index: 965277 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0234. Min Act: -0.0001

Data Index: 868091 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1330960 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0217. Min Act: -0.0001

Data Index: 656773 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0214. Min Act: -0.0001

Data Index: 991357 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0217. Min Act: -0.0001

Data Index: 783643 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0210. Min Act: -0.0001

Data Index: 764296 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0222. Min Act: -0.0001

Data Index: 835750 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0209. Min Act: -0.0001

Data Index: 105370 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0189. Min Act: -0.0001

Data Index: 718632 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0214. Min Act: -0.0001

Data Index: 340450 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0202. Min Act: -0.0001

Data Index: 545717 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1526883 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0195. Min Act: -0.0001

Data Index: 461212 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0191. Min Act: -0.0001

Data Index: 6167 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1164088 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0196. Min Act: -0.0001

Data Index: 31935 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0195. Min Act: -0.0001

Data Index: 172134 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1201616 (C4 (Web Text))

Max Activating Token Index: 219