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

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

Neuron 2832 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0003

Data Index: 1155360 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1405. Min Act: -0.0003

Data Index: 158074 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1264. Min Act: -0.0003

Data Index: 358648 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1216. Min Act: -0.0003

Data Index: 660274 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1221. Min Act: -0.0003

Data Index: 304633 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1196. Min Act: -0.0003

Data Index: 66731 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1219. Min Act: -0.0003

Data Index: 804330 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1267. Min Act: -0.0003

Data Index: 46182 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1209. Min Act: -0.0003

Data Index: 403190 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1204. Min Act: -0.0003

Data Index: 593603 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1159. Min Act: -0.0003

Data Index: 207517 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1201. Min Act: -0.0003

Data Index: 121051 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1197. Min Act: -0.0003

Data Index: 1034857 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1195. Min Act: -0.0003

Data Index: 163200 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1154. Min Act: -0.0003

Data Index: 815049 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1005140 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1184. Min Act: -0.0003

Data Index: 109184 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1271. Min Act: -0.0003

Data Index: 374459 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1178. Min Act: -0.0003

Data Index: 1182123 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1171. Min Act: -0.0003

Data Index: 526987 (C4 (Web Text))

Max Activating Token Index: 466