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

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

Neuron 3743 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0265. Min Act: -0.0001

Data Index: 13426 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0284. Min Act: -0.0001

Data Index: 484967 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0289. Min Act: -0.0001

Data Index: 592774 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0235. Min Act: -0.0000

Data Index: 27057 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0280. Min Act: -0.0000

Data Index: 236059 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0243. Min Act: -0.0001

Data Index: 718736 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0247. Min Act: -0.0000

Data Index: 300801 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1171629 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0221. Min Act: -0.0001

Data Index: 956951 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1188830 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1603828 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0218. Min Act: -0.0001

Data Index: 454813 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0280. Min Act: -0.0000

Data Index: 1323657 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0205. Min Act: -0.0001

Data Index: 311280 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0211. Min Act: -0.0001

Data Index: 50710 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1455880 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0200. Min Act: -0.0000

Data Index: 1007304 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0208. Min Act: -0.0001

Data Index: 494487 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1442140 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0222. Min Act: -0.0000

Data Index: 72923 (C4 (Web Text))

Max Activating Token Index: 172