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

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

Neuron 4511 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: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1260784 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1588428 (Python Code)

Max Activating Token Index: 571

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0233. Min Act: -0.0003

Data Index: 304304 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0228. Min Act: -0.0003

Data Index: 316228 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1045485 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0207. Min Act: -0.0003

Data Index: 715850 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1650489 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1577316 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0206. Min Act: -0.0003

Data Index: 7294 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0205. Min Act: -0.0003

Data Index: 630054 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1042416 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0204. Min Act: -0.0003

Data Index: 95802 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1220415 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1600498 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0189. Min Act: -0.0002

Data Index: 16095 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0201. Min Act: -0.0003

Data Index: 518521 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1020881 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1614929 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0192. Min Act: -0.0003

Data Index: 795790 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0186. Min Act: -0.0003

Data Index: 636530 (C4 (Web Text))

Max Activating Token Index: 60