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

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

Neuron 2945 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1453. Min Act: -0.0003

Data Index: 787663 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1428. Min Act: -0.0003

Data Index: 1053572 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1367. Min Act: -0.0003

Data Index: 677202 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1337. Min Act: -0.0003

Data Index: 590080 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1326. Min Act: -0.0003

Data Index: 544815 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1321. Min Act: -0.0003

Data Index: 247111 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1300. Min Act: -0.0003

Data Index: 82483 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1266. Min Act: -0.0003

Data Index: 909965 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1270. Min Act: -0.0003

Data Index: 885994 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1212. Min Act: -0.0003

Data Index: 31257 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1256. Min Act: -0.0003

Data Index: 947321 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1241. Min Act: -0.0002

Data Index: 742417 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1234. Min Act: -0.0003

Data Index: 127417 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1227. Min Act: -0.0003

Data Index: 535159 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1219. Min Act: -0.0003

Data Index: 1165725 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1211. Min Act: -0.0003

Data Index: 723693 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1225. Min Act: -0.0003

Data Index: 1316835 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1215. Min Act: -0.0003

Data Index: 639202 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1170. Min Act: -0.0003

Data Index: 1041833 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1167. Min Act: -0.0003

Data Index: 150079 (C4 (Web Text))

Max Activating Token Index: 80