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

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

Neuron 1395 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: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0001

Data Index: 385370 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0511. Min Act: -0.0001

Data Index: 363765 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0334. Min Act: -0.0001

Data Index: 976592 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0304. Min Act: -0.0001

Data Index: 303339 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0267. Min Act: -0.0001

Data Index: 213865 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0244. Min Act: -0.0001

Data Index: 880689 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1007257 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1293338 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1578929 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1155829 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0226. Min Act: -0.0001

Data Index: 650835 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1328620 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1085824 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0239. Min Act: -0.0001

Data Index: 158342 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0221. Min Act: -0.0001

Data Index: 69894 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0175. Min Act: -0.0001

Data Index: 788339 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0248. Min Act: -0.0001

Data Index: 97205 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0240. Min Act: -0.0001

Data Index: 454147 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1073706 (C4 (Web Text))

Max Activating Token Index: 373