Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 682 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0004

Data Index: 198942 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1396132 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0204. Min Act: -0.0004

Data Index: 766092 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1279706 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0202. Min Act: -0.0004

Data Index: 251168 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1183164 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1208277 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0203. Min Act: -0.0004

Data Index: 910683 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0184. Min Act: -0.0004

Data Index: 218570 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1273401 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0203. Min Act: -0.0004

Data Index: 131850 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0176. Min Act: -0.0004

Data Index: 726702 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0225. Min Act: -0.0004

Data Index: 326877 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0210. Min Act: -0.0004

Data Index: 153739 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0185. Min Act: -0.0004

Data Index: 387887 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0210. Min Act: -0.0004

Data Index: 956934 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0203. Min Act: -0.0004

Data Index: 331360 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0218. Min Act: -0.0004

Data Index: 399798 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0004

Data Index: 426539 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1184815 (C4 (Web Text))

Max Activating Token Index: 961