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

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

Neuron 3252 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: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0001

Data Index: 181229 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0283. Min Act: -0.0001

Data Index: 262555 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1229220 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0001

Data Index: 925416 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0251. Min Act: -0.0001

Data Index: 654583 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0255. Min Act: -0.0001

Data Index: 90275 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0236. Min Act: -0.0001

Data Index: 364689 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0243. Min Act: -0.0001

Data Index: 401528 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0225. Min Act: -0.0001

Data Index: 194938 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0222. Min Act: -0.0001

Data Index: 809266 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0222. Min Act: -0.0001

Data Index: 366312 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0228. Min Act: -0.0001

Data Index: 1180724 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0214. Min Act: -0.0001

Data Index: 919395 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0237. Min Act: -0.0001

Data Index: 623377 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0218. Min Act: -0.0001

Data Index: 325241 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1206126 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0192. Min Act: -0.0001

Data Index: 632922 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1162113 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0197. Min Act: -0.0001

Data Index: 976183 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0204. Min Act: -0.0001

Data Index: 686854 (C4 (Web Text))

Max Activating Token Index: 899