Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1253 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0002

Data Index: 896752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0370. Min Act: -0.0001

Data Index: 824630 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1450850 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1580914 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1443646 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0313. Min Act: -0.0001

Data Index: 327912 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1106247 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0302. Min Act: -0.0001

Data Index: 475209 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1137939 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0273. Min Act: -0.0002

Data Index: 213012 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0338. Min Act: -0.0000

Data Index: 667991 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1319729 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0286. Min Act: -0.0002

Data Index: 995559 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1393185 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0248. Min Act: -0.0002

Data Index: 386056 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1496847 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0250. Min Act: -0.0002

Data Index: 705218 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0266. Min Act: -0.0002

Data Index: 234218 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1551476 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1446353 (Python Code)

Max Activating Token Index: 964