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

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

Neuron 4746 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0218. Min Act: -0.0002

Data Index: 616595 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0002

Data Index: 40085 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0192. Min Act: -0.0002

Data Index: 571590 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0206. Min Act: -0.0002

Data Index: 682112 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0199. Min Act: -0.0002

Data Index: 342118 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1475228 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1600271 (Python Code)

Max Activating Token Index: 835

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0204. Min Act: -0.0002

Data Index: 83411 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0195. Min Act: -0.0002

Data Index: 87095 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0209. Min Act: -0.0002

Data Index: 117949 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1293387 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0189. Min Act: -0.0002

Data Index: 926467 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0183. Min Act: -0.0002

Data Index: 28919 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0152. Min Act: -0.0002

Data Index: 408011 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0187. Min Act: -0.0002

Data Index: 480332 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0181. Min Act: -0.0002

Data Index: 147805 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1315533 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0192. Min Act: -0.0002

Data Index: 664434 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1619225 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0168. Min Act: -0.0002

Data Index: 529835 (C4 (Web Text))

Max Activating Token Index: 573