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

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

Neuron 3405 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: 0.0248. Min Range: -0.0248

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1653068 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1398281 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1322396 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1499382 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0197. Min Act: -0.0003

Data Index: 630426 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1524791 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1169485 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0200. Min Act: -0.0003

Data Index: 648913 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0215. Min Act: -0.0003

Data Index: 509836 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0205. Min Act: -0.0003

Data Index: 865173 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0189. Min Act: -0.0003

Data Index: 904514 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1411979 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0195. Min Act: -0.0003

Data Index: 630405 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1456609 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1648698 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0201. Min Act: -0.0004

Data Index: 594532 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0208. Min Act: -0.0003

Data Index: 604694 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0203. Min Act: -0.0003

Data Index: 427573 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0186. Min Act: -0.0003

Data Index: 819153 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0198. Min Act: -0.0003

Data Index: 718299 (C4 (Web Text))

Max Activating Token Index: 11