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

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

Neuron 742 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0002

Data Index: 913715 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1592386 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1388609 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1584537 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1632982 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1045216 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1483307 (Python Code)

Max Activating Token Index: 209

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1291060 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1402953 (Python Code)

Max Activating Token Index: 409

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1440247 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1530578 (Python Code)

Max Activating Token Index: 409

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1655339 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0181. Min Act: -0.0002

Data Index: 725915 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1495097 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1448703 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0185. Min Act: -0.0002

Data Index: 205682 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1272621 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0194. Min Act: -0.0002

Data Index: 622638 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0180. Min Act: -0.0002

Data Index: 111571 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1300919 (C4 (Web Text))

Max Activating Token Index: 254