Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 254 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1136409 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1073553 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0239. Min Act: -0.0001

Data Index: 785691 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1330460 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1951 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0209. Min Act: -0.0002

Data Index: 530021 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0196. Min Act: -0.0001

Data Index: 810658 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0187. Min Act: -0.0001

Data Index: 642659 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0197. Min Act: -0.0001

Data Index: 358199 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0193. Min Act: -0.0001

Data Index: 532566 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0183. Min Act: -0.0001

Data Index: 704614 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0198. Min Act: -0.0001

Data Index: 380500 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0184. Min Act: -0.0001

Data Index: 55157 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0195. Min Act: -0.0001

Data Index: 718446 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1148513 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0194. Min Act: -0.0001

Data Index: 633121 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0184. Min Act: -0.0001

Data Index: 884498 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1283323 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1012899 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0173. Min Act: -0.0001

Data Index: 611764 (C4 (Web Text))

Max Activating Token Index: 32