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

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

Neuron 2686 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: 0.0287. Min Range: -0.0287

Max Act: 0.0284. Min Act: -0.0002

Data Index: 131793 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0002

Data Index: 633136 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1230105 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0262. Min Act: -0.0002

Data Index: 31137 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0197. Min Act: -0.0002

Data Index: 340532 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0234. Min Act: -0.0002

Data Index: 447279 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0247. Min Act: -0.0002

Data Index: 121516 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1182511 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1184590 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0200. Min Act: -0.0002

Data Index: 154189 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0213. Min Act: -0.0002

Data Index: 729239 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0222. Min Act: -0.0002

Data Index: 176910 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1082749 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0211. Min Act: -0.0002

Data Index: 202007 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1232517 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0198. Min Act: -0.0002

Data Index: 933435 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0223. Min Act: -0.0002

Data Index: 458528 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0229. Min Act: -0.0002

Data Index: 351226 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0204. Min Act: -0.0002

Data Index: 162363 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1011865 (C4 (Web Text))

Max Activating Token Index: 974