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

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

Neuron 495 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: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0006

Data Index: 22158 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0248. Min Act: -0.0006

Data Index: 970455 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0246. Min Act: -0.0006

Data Index: 580882 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0247. Min Act: -0.0006

Data Index: 320406 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1577718 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0243. Min Act: -0.0006

Data Index: 955036 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0232. Min Act: -0.0006

Data Index: 695076 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0225. Min Act: -0.0006

Data Index: 221088 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1200622 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0225. Min Act: -0.0006

Data Index: 847835 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0228. Min Act: -0.0006

Data Index: 993504 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1011485 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0213. Min Act: -0.0006

Data Index: 302489 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1279470 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0006

Data Index: 628666 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1063888 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0218. Min Act: -0.0006

Data Index: 642687 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0213. Min Act: -0.0006

Data Index: 650486 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1116216 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0006

Data Index: 281699 (C4 (Web Text))

Max Activating Token Index: 188