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

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

Neuron 497 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0003

Data Index: 617213 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0251. Min Act: -0.0003

Data Index: 220353 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0254. Min Act: -0.0003

Data Index: 853082 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1061582 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0251. Min Act: -0.0003

Data Index: 750837 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0241. Min Act: -0.0003

Data Index: 158512 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0247. Min Act: -0.0003

Data Index: 631188 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0250. Min Act: -0.0003

Data Index: 404219 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0251. Min Act: -0.0003

Data Index: 387341 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1065349 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0244. Min Act: -0.0003

Data Index: 820771 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1333552 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0248. Min Act: -0.0003

Data Index: 30970 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1061947 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0249. Min Act: -0.0003

Data Index: 446332 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1176112 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1601623 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1207349 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0235. Min Act: -0.0003

Data Index: 372726 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1190842 (C4 (Web Text))

Max Activating Token Index: 871