Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 579 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1535760 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0234. Min Act: -0.0005

Data Index: 828433 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0230. Min Act: -0.0005

Data Index: 1100979 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0220. Min Act: -0.0005

Data Index: 160617 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0209. Min Act: -0.0005

Data Index: 1597373 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0213. Min Act: -0.0005

Data Index: 1553482 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0212. Min Act: -0.0005

Data Index: 660524 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0205. Min Act: -0.0005

Data Index: 1605187 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1357674 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1122259 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0215. Min Act: -0.0004

Data Index: 1512874 (Python Code)

Max Activating Token Index: 356

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0194. Min Act: -0.0005

Data Index: 1561954 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0203. Min Act: -0.0005

Data Index: 519853 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1183395 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1114323 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0197. Min Act: -0.0005

Data Index: 1229463 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1513686 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0218. Min Act: -0.0005

Data Index: 1445086 (Python Code)

Max Activating Token Index: 446

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1339562 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1092859 (C4 (Web Text))

Max Activating Token Index: 1011