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

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

Neuron 5966 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0001

Data Index: 245521 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0299. Min Act: -0.0001

Data Index: 292515 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1145747 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0001

Data Index: 625489 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1336145 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0001

Data Index: 457243 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1300889 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1573603 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0001

Data Index: 975578 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0277. Min Act: -0.0001

Data Index: 542760 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1241224 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1209147 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0207. Min Act: -0.0001

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0001

Data Index: 587628 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1351108 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0226. Min Act: -0.0001

Data Index: 932432 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0243. Min Act: -0.0001

Data Index: 435660 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0236. Min Act: -0.0002

Data Index: 950927 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0236. Min Act: -0.0001

Data Index: 600616 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1345417 (C4 (Web Text))

Max Activating Token Index: 5