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

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

Neuron 3888 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0003

Data Index: 914353 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0251. Min Act: -0.0003

Data Index: 948635 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0236. Min Act: -0.0003

Data Index: 587823 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1630071 (Python Code)

Max Activating Token Index: 109

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0236. Min Act: -0.0003

Data Index: 264142 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1341760 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1549223 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1067106 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0003

Data Index: 636253 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1060403 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0213. Min Act: -0.0003

Data Index: 219263 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0218. Min Act: -0.0003

Data Index: 256006 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0222. Min Act: -0.0003

Data Index: 541248 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1173150 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0219. Min Act: -0.0003

Data Index: 970618 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1414094 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1483386 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1409120 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1029139 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0004

Data Index: 591925 (C4 (Web Text))

Max Activating Token Index: 766