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

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

Neuron 4918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0330. Min Act: -0.0003

Data Index: 781232 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0003

Data Index: 111475 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0235. Min Act: -0.0003

Data Index: 6539 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1223589 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0228. Min Act: -0.0003

Data Index: 28867 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0243. Min Act: -0.0003

Data Index: 596511 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0213. Min Act: -0.0003

Data Index: 888838 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0215. Min Act: -0.0003

Data Index: 500811 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0211. Min Act: -0.0002

Data Index: 641028 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0196. Min Act: -0.0003

Data Index: 410682 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1066590 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0207. Min Act: -0.0002

Data Index: 886009 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0172. Min Act: -0.0003

Data Index: 765625 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0159. Min Act: -0.0003

Data Index: 198385 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1109991 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1237874 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0173. Min Act: -0.0003

Data Index: 747003 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1068116 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0187. Min Act: -0.0003

Data Index: 448926 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1056015 (C4 (Web Text))

Max Activating Token Index: 457