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

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

Neuron 4514 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0002

Data Index: 714522 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0228. Min Act: -0.0002

Data Index: 779613 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0211. Min Act: -0.0002

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0219. Min Act: -0.0002

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1486271 (Python Code)

Max Activating Token Index: 480

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0203. Min Act: -0.0002

Data Index: 87421 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0205. Min Act: -0.0002

Data Index: 578810 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0199. Min Act: -0.0002

Data Index: 82746 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0201. Min Act: -0.0002

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0201. Min Act: -0.0002

Data Index: 863776 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1186697 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1462219 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0197. Min Act: -0.0002

Data Index: 902446 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0200. Min Act: -0.0002

Data Index: 478208 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0201. Min Act: -0.0002

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1384403 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1298668 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0190. Min Act: -0.0002

Data Index: 577155 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1122273 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1464396 (Python Code)

Max Activating Token Index: 341