Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3101 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1240389 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1384. Min Act: -0.0001

Data Index: 829987 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1364. Min Act: -0.0001

Data Index: 835002 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1229. Min Act: -0.0001

Data Index: 637462 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1062807 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1250. Min Act: -0.0001

Data Index: 920739 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1266. Min Act: -0.0001

Data Index: 117132 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1179. Min Act: -0.0001

Data Index: 268641 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1233. Min Act: -0.0001

Data Index: 792655 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1197794 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1224. Min Act: -0.0001

Data Index: 975129 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0979. Min Act: -0.0001

Data Index: 950133 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1180. Min Act: -0.0001

Data Index: 301736 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1214. Min Act: -0.0001

Data Index: 898211 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1259. Min Act: -0.0001

Data Index: 786470 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1167. Min Act: -0.0001

Data Index: 914851 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1134654 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1216548 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1131. Min Act: -0.0001

Data Index: 635584 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1158. Min Act: -0.0001

Data Index: 844547 (C4 (Web Text))

Max Activating Token Index: 411