Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 908 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1137710 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0299. Min Act: -0.0005

Data Index: 145625 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1199495 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1275855 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0274. Min Act: -0.0006

Data Index: 435632 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0269. Min Act: -0.0006

Data Index: 734044 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0274. Min Act: -0.0006

Data Index: 454195 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0272. Min Act: -0.0006

Data Index: 954965 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0271. Min Act: -0.0005

Data Index: 613 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1279260 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1120775 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0258. Min Act: -0.0006

Data Index: 505032 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0266. Min Act: -0.0006

Data Index: 519042 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0266. Min Act: -0.0006

Data Index: 809614 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0275. Min Act: -0.0006

Data Index: 797135 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0264. Min Act: -0.0006

Data Index: 63422 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0262. Min Act: -0.0006

Data Index: 835000 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0256. Min Act: -0.0006

Data Index: 998217 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0259. Min Act: -0.0006

Data Index: 93309 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0258. Min Act: -0.0006

Data Index: 999197 (C4 (Web Text))

Max Activating Token Index: 567