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

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

Neuron 923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0002

Data Index: 923165 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0300. Min Act: -0.0002

Data Index: 789575 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0302. Min Act: -0.0002

Data Index: 268290 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0275. Min Act: -0.0002

Data Index: 193976 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1077968 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0242. Min Act: -0.0002

Data Index: 791572 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0248. Min Act: -0.0002

Data Index: 439700 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1570933 (Python Code)

Max Activating Token Index: 824

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0254. Min Act: -0.0002

Data Index: 199863 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1611958 (Python Code)

Max Activating Token Index: 183

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1422782 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1563651 (Python Code)

Max Activating Token Index: 619

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1488047 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0234. Min Act: -0.0002

Data Index: 280737 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0213. Min Act: -0.0002

Data Index: 220792 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0235. Min Act: -0.0002

Data Index: 908839 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0215. Min Act: -0.0002

Data Index: 85216 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1285566 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1500582 (Python Code)

Max Activating Token Index: 683

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0224. Min Act: -0.0002

Data Index: 444856 (C4 (Web Text))

Max Activating Token Index: 415