Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6108 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1222878 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1241244 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0229. Min Act: -0.0001

Data Index: 462641 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0236. Min Act: -0.0001

Data Index: 968241 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0226. Min Act: -0.0001

Data Index: 865856 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0218. Min Act: -0.0001

Data Index: 374381 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0234. Min Act: -0.0001

Data Index: 731886 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0215. Min Act: -0.0001

Data Index: 381384 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0218. Min Act: -0.0001

Data Index: 222265 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0226. Min Act: -0.0001

Data Index: 677840 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0223. Min Act: -0.0001

Data Index: 199748 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0212. Min Act: -0.0001

Data Index: 420912 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0206. Min Act: -0.0001

Data Index: 422442 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1260102 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0209. Min Act: -0.0001

Data Index: 409624 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1030995 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0201. Min Act: -0.0001

Data Index: 879946 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0208. Min Act: -0.0001

Data Index: 568206 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1600154 (Python Code)

Max Activating Token Index: 483

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0208. Min Act: -0.0001

Data Index: 60725 (C4 (Web Text))

Max Activating Token Index: 611