Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0002

Data Index: 417312 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0279. Min Act: -0.0002

Data Index: 367706 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0301. Min Act: -0.0001

Data Index: 471878 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0297. Min Act: -0.0002

Data Index: 612472 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0254. Min Act: -0.0001

Data Index: 931859 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0245. Min Act: -0.0002

Data Index: 931821 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0237. Min Act: -0.0001

Data Index: 896994 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1116910 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0245. Min Act: -0.0001

Data Index: 940863 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0252. Min Act: -0.0001

Data Index: 816693 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1413494 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1215084 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0001

Data Index: 118476 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0227. Min Act: -0.0002

Data Index: 801910 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1067569 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0234. Min Act: -0.0001

Data Index: 874727 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0002

Data Index: 436508 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1183714 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0232. Min Act: -0.0002

Data Index: 773816 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1170695 (C4 (Web Text))

Max Activating Token Index: 109