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

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

Neuron 2750 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: 0.0237. Min Range: -0.0237

Max Act: 0.0224. Min Act: -0.0003

Data Index: 265907 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1255983 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1349175 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0003

Data Index: 994965 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1241976 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1022817 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1039308 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0218. Min Act: -0.0003

Data Index: 102675 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1157745 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1239149 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0201. Min Act: -0.0003

Data Index: 935636 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0189. Min Act: -0.0003

Data Index: 706872 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1447148 (Python Code)

Max Activating Token Index: 573

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0195. Min Act: -0.0003

Data Index: 424498 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1108758 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0190. Min Act: -0.0003

Data Index: 158626 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0190. Min Act: -0.0003

Data Index: 301900 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1193015 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0202. Min Act: -0.0003

Data Index: 726811 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0170. Min Act: -0.0003

Data Index: 134175 (C4 (Web Text))

Max Activating Token Index: 891