Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 20 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0218. Min Act: -0.0003

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0003

Data Index: 444591 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1358090 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1330055 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1015418 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1175642 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0182. Min Act: -0.0003

Data Index: 927340 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0193. Min Act: -0.0003

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1249861 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0180. Min Act: -0.0003

Data Index: 352487 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1214225 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0180. Min Act: -0.0003

Data Index: 565531 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0173. Min Act: -0.0003

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0175. Min Act: -0.0003

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0195. Min Act: -0.0003

Data Index: 172803 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1576042 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0171. Min Act: -0.0003

Data Index: 871555 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0163. Min Act: -0.0003

Data Index: 19083 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0180. Min Act: -0.0003

Data Index: 719324 (C4 (Web Text))

Max Activating Token Index: 1014