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

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

Neuron 77 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1303304 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0299. Min Act: -0.0000

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1188627 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0262. Min Act: -0.0000

Data Index: 986452 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0247. Min Act: -0.0000

Data Index: 904685 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0292. Min Act: -0.0000

Data Index: 59140 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0226. Min Act: -0.0000

Data Index: 48955 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0245. Min Act: -0.0000

Data Index: 327188 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0231. Min Act: -0.0000

Data Index: 651039 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0263. Min Act: -0.0000

Data Index: 550073 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0244. Min Act: -0.0000

Data Index: 980990 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1424507 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0250. Min Act: -0.0000

Data Index: 539077 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0241. Min Act: -0.0000

Data Index: 886094 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0216. Min Act: -0.0000

Data Index: 623827 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0207. Min Act: -0.0000

Data Index: 88404 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0232. Min Act: -0.0000

Data Index: 44222 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1079590 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0257. Min Act: -0.0000

Data Index: 660433 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0223. Min Act: -0.0000

Data Index: 415439 (C4 (Web Text))

Max Activating Token Index: 156