Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1291. Min Act: -0.0001

Data Index: 531088 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1186. Min Act: -0.0001

Data Index: 279802 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0001

Data Index: 678650 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1195655 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1217. Min Act: -0.0001

Data Index: 679369 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1337399 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1215869 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1127. Min Act: -0.0002

Data Index: 208387 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1148. Min Act: -0.0002

Data Index: 393015 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1282878 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1124. Min Act: -0.0002

Data Index: 1029873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1184828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1091. Min Act: -0.0002

Data Index: 308675 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0958. Min Act: -0.0002

Data Index: 72123 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1012. Min Act: -0.0001

Data Index: 625229 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1292453 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1028. Min Act: -0.0002

Data Index: 398001 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0916. Min Act: -0.0001

Data Index: 69041 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1033. Min Act: -0.0002

Data Index: 252277 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1035. Min Act: -0.0001

Data Index: 831800 (C4 (Web Text))

Max Activating Token Index: 339