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

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

Neuron 789 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0001

Data Index: 360008 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1220976 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1228304 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0200. Min Act: -0.0001

Data Index: 137631 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0188. Min Act: -0.0001

Data Index: 721722 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0190. Min Act: -0.0001

Data Index: 837681 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1499304 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0184. Min Act: -0.0001

Data Index: 869139 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0180. Min Act: -0.0001

Data Index: 133504 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0185. Min Act: -0.0001

Data Index: 742645 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1069607 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0173. Min Act: -0.0001

Data Index: 556971 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0183. Min Act: -0.0001

Data Index: 38252 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0176. Min Act: -0.0001

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1409770 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0181. Min Act: -0.0001

Data Index: 227250 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1032303 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0173. Min Act: -0.0000

Data Index: 1247564 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0172. Min Act: -0.0001

Data Index: 760191 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0170. Min Act: -0.0001

Data Index: 783621 (C4 (Web Text))

Max Activating Token Index: 521