Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 213 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0002

Data Index: 581712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1048838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0313. Min Act: -0.0003

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0296. Min Act: -0.0003

Data Index: 736115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0290. Min Act: -0.0003

Data Index: 824604 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0290. Min Act: -0.0002

Data Index: 897752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0262. Min Act: -0.0003

Data Index: 828640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1135587 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0267. Min Act: -0.0003

Data Index: 668934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0268. Min Act: -0.0003

Data Index: 385102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0274. Min Act: -0.0003

Data Index: 418342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1272887 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0264. Min Act: -0.0003

Data Index: 610295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0237. Min Act: -0.0002

Data Index: 104941 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1329680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0225. Min Act: -0.0003

Data Index: 677501 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0242. Min Act: -0.0002

Data Index: 193402 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0241. Min Act: -0.0003

Data Index: 169366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1014316 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1106147 (C4 (Web Text))

Max Activating Token Index: 1023