Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1372 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0003

Data Index: 85775 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0213. Min Act: -0.0004

Data Index: 913342 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1582574 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1015396 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0211. Min Act: -0.0004

Data Index: 540587 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0215. Min Act: -0.0003

Data Index: 459419 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0004

Data Index: 897816 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0004

Data Index: 88931 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1509962 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1591081 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1005555 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0004

Data Index: 10226 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0004

Data Index: 1382595 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0194. Min Act: -0.0004

Data Index: 1467393 (Python Code)

Max Activating Token Index: 824

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0003

Data Index: 217287 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1598078 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1443163 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0194. Min Act: -0.0003

Data Index: 904698 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0004

Data Index: 326919 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1392997 (Python Code)

Max Activating Token Index: 1006