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

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

Neuron 3643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0002

Data Index: 514727 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0282. Min Act: -0.0002

Data Index: 587815 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0279. Min Act: -0.0002

Data Index: 366549 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1331065 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0269. Min Act: -0.0002

Data Index: 659846 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0257. Min Act: -0.0002

Data Index: 114754 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0248. Min Act: -0.0002

Data Index: 337592 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1292444 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1164753 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0248. Min Act: -0.0002

Data Index: 482768 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0238. Min Act: -0.0002

Data Index: 89635 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1091286 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1239902 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0243. Min Act: -0.0002

Data Index: 425849 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0243. Min Act: -0.0002

Data Index: 329130 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0227. Min Act: -0.0002

Data Index: 882897 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0235. Min Act: -0.0002

Data Index: 180263 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0239. Min Act: -0.0002

Data Index: 792873 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0222. Min Act: -0.0002

Data Index: 194409 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0220. Min Act: -0.0002

Data Index: 144899 (C4 (Web Text))

Max Activating Token Index: 542