Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1524 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0003

Data Index: 187635 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0003

Data Index: 773556 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0224. Min Act: -0.0003

Data Index: 899733 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0228. Min Act: -0.0003

Data Index: 444235 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1087478 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1299903 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1136981 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0200. Min Act: -0.0003

Data Index: 37564 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0211. Min Act: -0.0003

Data Index: 996092 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0205. Min Act: -0.0003

Data Index: 130045 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1049187 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0215. Min Act: -0.0002

Data Index: 682514 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0187. Min Act: -0.0003

Data Index: 923238 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0208. Min Act: -0.0003

Data Index: 83213 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1185691 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1148939 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0208. Min Act: -0.0003

Data Index: 891030 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1026094 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0215. Min Act: -0.0003

Data Index: 876570 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0197. Min Act: -0.0003

Data Index: 292301 (C4 (Web Text))

Max Activating Token Index: 316