Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 648 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0305. Min Act: -0.0006

Data Index: 664855 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1218089 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0289. Min Act: -0.0006

Data Index: 172718 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0276. Min Act: -0.0006

Data Index: 696263 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0287. Min Act: -0.0006

Data Index: 792031 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0006

Data Index: 692884 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1184821 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1237706 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0279. Min Act: -0.0006

Data Index: 950259 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0268. Min Act: -0.0006

Data Index: 425642 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0258. Min Act: -0.0006

Data Index: 15806 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0267. Min Act: -0.0006

Data Index: 457092 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0246. Min Act: -0.0006

Data Index: 944493 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0255. Min Act: -0.0006

Data Index: 118970 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0271. Min Act: -0.0006

Data Index: 220210 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0295. Min Act: -0.0006

Data Index: 667791 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1242053 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0243. Min Act: -0.0006

Data Index: 602267 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1266580 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0273. Min Act: -0.0006

Data Index: 124855 (C4 (Web Text))

Max Activating Token Index: 582