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

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

Neuron 550 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0002

Data Index: 57266 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0277. Min Act: -0.0001

Data Index: 222514 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0265. Min Act: -0.0002

Data Index: 722915 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0257. Min Act: -0.0001

Data Index: 789489 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0249. Min Act: -0.0002

Data Index: 548499 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0248. Min Act: -0.0002

Data Index: 12205 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0246. Min Act: -0.0002

Data Index: 418295 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0242. Min Act: -0.0002

Data Index: 947576 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0234. Min Act: -0.0002

Data Index: 761660 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1223160 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1156684 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0236. Min Act: -0.0002

Data Index: 388387 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1253722 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0228. Min Act: -0.0002

Data Index: 509361 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0228. Min Act: -0.0002

Data Index: 490044 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0232. Min Act: -0.0002

Data Index: 79141 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0227. Min Act: -0.0002

Data Index: 760032 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0227. Min Act: -0.0001

Data Index: 883939 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1139793 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0226. Min Act: -0.0002

Data Index: 731821 (C4 (Web Text))

Max Activating Token Index: 742