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

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

Neuron 5628 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: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0001

Data Index: 730022 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0282. Min Act: -0.0001

Data Index: 125707 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1277685 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0267. Min Act: -0.0001

Data Index: 89724 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0232. Min Act: -0.0001

Data Index: 530424 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1092293 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0230. Min Act: -0.0001

Data Index: 373276 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0214. Min Act: -0.0001

Data Index: 471269 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1354768 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0203. Min Act: -0.0001

Data Index: 202143 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0190. Min Act: -0.0001

Data Index: 465949 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0194. Min Act: -0.0001

Data Index: 9321 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0187. Min Act: -0.0001

Data Index: 291550 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1597559 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0168. Min Act: -0.0001

Data Index: 151113 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0173. Min Act: -0.0001

Data Index: 832691 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0153. Min Act: -0.0001

Data Index: 804495 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1117069 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1164883 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0180. Min Act: -0.0001

Data Index: 73707 (C4 (Web Text))

Max Activating Token Index: 209