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

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

Neuron 4287 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: 0.0237. Min Range: -0.0237

Max Act: 0.0230. Min Act: -0.0001

Data Index: 565591 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0227. Min Act: -0.0001

Data Index: 248878 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0001

Data Index: 612756 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0222. Min Act: -0.0001

Data Index: 796503 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0233. Min Act: -0.0001

Data Index: 72870 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0230. Min Act: -0.0001

Data Index: 524027 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0210. Min Act: -0.0001

Data Index: 513777 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0199. Min Act: -0.0001

Data Index: 165579 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0215. Min Act: -0.0001

Data Index: 95204 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0208. Min Act: -0.0001

Data Index: 445337 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0175. Min Act: -0.0001

Data Index: 289082 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0177. Min Act: -0.0001

Data Index: 444568 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1152356 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1301900 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1302025 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1228072 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0184. Min Act: -0.0001

Data Index: 655895 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0202. Min Act: -0.0001

Data Index: 568584 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0197. Min Act: -0.0001

Data Index: 593148 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1295104 (C4 (Web Text))

Max Activating Token Index: 480