Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 120 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1190807 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0223. Min Act: -0.0003

Data Index: 471466 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0210. Min Act: -0.0003

Data Index: 989033 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1196659 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0206. Min Act: -0.0002

Data Index: 238185 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1297749 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0003

Data Index: 671689 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0205. Min Act: -0.0003

Data Index: 911236 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0200. Min Act: -0.0003

Data Index: 302511 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0198. Min Act: -0.0002

Data Index: 550640 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0198. Min Act: -0.0003

Data Index: 490310 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0198. Min Act: -0.0003

Data Index: 151121 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0196. Min Act: -0.0003

Data Index: 433564 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0189. Min Act: -0.0003

Data Index: 311567 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0183. Min Act: -0.0003

Data Index: 825428 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0186. Min Act: -0.0002

Data Index: 966827 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0184. Min Act: -0.0003

Data Index: 416737 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1312272 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0180. Min Act: -0.0003

Data Index: 163235 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1160286 (C4 (Web Text))

Max Activating Token Index: 198