Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 607 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0001

Data Index: 932585 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0302. Min Act: -0.0001

Data Index: 307708 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0305. Min Act: -0.0001

Data Index: 826219 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0278. Min Act: -0.0001

Data Index: 558125 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0233. Min Act: -0.0001

Data Index: 421348 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0254. Min Act: -0.0001

Data Index: 395623 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1105419 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0251. Min Act: -0.0001

Data Index: 251730 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0253. Min Act: -0.0001

Data Index: 263035 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0287. Min Act: -0.0001

Data Index: 640740 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0247. Min Act: -0.0001

Data Index: 837942 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0218. Min Act: -0.0001

Data Index: 315398 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0245. Min Act: -0.0001

Data Index: 704148 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0232. Min Act: -0.0001

Data Index: 797741 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0233. Min Act: -0.0001

Data Index: 242327 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0222. Min Act: -0.0001

Data Index: 948033 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0204. Min Act: -0.0001

Data Index: 757579 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0203. Min Act: -0.0001

Data Index: 951968 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1034502 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0191. Min Act: -0.0001

Data Index: 187702 (C4 (Web Text))

Max Activating Token Index: 194