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

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

Neuron 1946 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: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0002

Data Index: 720792 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0279. Min Act: -0.0002

Data Index: 416315 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0279. Min Act: -0.0002

Data Index: 274019 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1349202 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0267. Min Act: -0.0002

Data Index: 795318 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0273. Min Act: -0.0002

Data Index: 889148 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0253. Min Act: -0.0002

Data Index: 305984 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0256. Min Act: -0.0002

Data Index: 341914 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1194244 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0231. Min Act: -0.0002

Data Index: 339113 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0241. Min Act: -0.0002

Data Index: 906115 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0250. Min Act: -0.0002

Data Index: 865232 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0234. Min Act: -0.0002

Data Index: 789225 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0232. Min Act: -0.0002

Data Index: 558852 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0226. Min Act: -0.0002

Data Index: 691192 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0243. Min Act: -0.0002

Data Index: 592395 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0242. Min Act: -0.0002

Data Index: 280257 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0207. Min Act: -0.0002

Data Index: 504575 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0221. Min Act: -0.0002

Data Index: 453953 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0211. Min Act: -0.0002

Data Index: 714831 (C4 (Web Text))

Max Activating Token Index: 195