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

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

Neuron 566 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: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0006

Data Index: 956854 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0317. Min Act: -0.0006

Data Index: 550192 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0302. Min Act: -0.0006

Data Index: 842013 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1262409 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1203237 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0269. Min Act: -0.0006

Data Index: 982205 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0263. Min Act: -0.0006

Data Index: 626577 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0246. Min Act: -0.0006

Data Index: 4325 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0204. Min Act: -0.0006

Data Index: 11687 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0250. Min Act: -0.0005

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0241. Min Act: -0.0006

Data Index: 807511 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0199. Min Act: -0.0006

Data Index: 360273 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0228. Min Act: -0.0006

Data Index: 821154 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0227. Min Act: -0.0006

Data Index: 293483 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0218. Min Act: -0.0006

Data Index: 104807 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0227. Min Act: -0.0006

Data Index: 339259 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0202. Min Act: -0.0006

Data Index: 517256 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0231. Min Act: -0.0006

Data Index: 667743 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0238. Min Act: -0.0006

Data Index: 655367 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1305761 (C4 (Web Text))

Max Activating Token Index: 17