Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1285 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0278. Min Act: -0.0006

Data Index: 359333 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0254. Min Act: -0.0006

Data Index: 677228 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0265. Min Act: -0.0006

Data Index: 553404 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1650499 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0252. Min Act: -0.0006

Data Index: 575740 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1447617 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1254913 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0243. Min Act: -0.0006

Data Index: 936408 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1246500 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0244. Min Act: -0.0006

Data Index: 926015 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0238. Min Act: -0.0006

Data Index: 925973 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1199503 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1382733 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1348909 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1484084 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1268199 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1007000 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1394538 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0226. Min Act: -0.0006

Data Index: 466533 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0226. Min Act: -0.0006

Data Index: 666514 (C4 (Web Text))

Max Activating Token Index: 451