Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 60 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0002

Data Index: 27562 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0198. Min Act: -0.0002

Data Index: 710751 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0193. Min Act: -0.0002

Data Index: 383462 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0192. Min Act: -0.0002

Data Index: 445299 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0192. Min Act: -0.0002

Data Index: 329907 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1268159 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0187. Min Act: -0.0002

Data Index: 249542 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0187. Min Act: -0.0002

Data Index: 962458 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0186. Min Act: -0.0002

Data Index: 614811 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1187491 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0185. Min Act: -0.0002

Data Index: 911100 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0182. Min Act: -0.0002

Data Index: 964216 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0183. Min Act: -0.0002

Data Index: 313166 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0179. Min Act: -0.0002

Data Index: 917094 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0177. Min Act: -0.0002

Data Index: 112775 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0176. Min Act: -0.0002

Data Index: 149765 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1054055 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0172. Min Act: -0.0002

Data Index: 929430 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1422687 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1081824 (C4 (Web Text))

Max Activating Token Index: 820