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

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

Neuron 4680 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: 0.0223. Min Range: -0.0223

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1060826 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0210. Min Act: -0.0002

Data Index: 836079 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0216. Min Act: -0.0002

Data Index: 531105 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0219. Min Act: -0.0002

Data Index: 778965 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1212809 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0002

Data Index: 618044 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1008139 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0171. Min Act: -0.0002

Data Index: 11154 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0203. Min Act: -0.0002

Data Index: 206471 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1304310 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1418285 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0202. Min Act: -0.0002

Data Index: 688420 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0183. Min Act: -0.0002

Data Index: 680804 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0182. Min Act: -0.0002

Data Index: 368079 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1130000 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0183. Min Act: -0.0002

Data Index: 405759 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1202617 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0197. Min Act: -0.0002

Data Index: 902749 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1221391 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0174. Min Act: -0.0002

Data Index: 579267 (C4 (Web Text))

Max Activating Token Index: 519