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

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

Neuron 4144 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0564. Min Act: -0.0002

Data Index: 686588 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1028207 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0487. Min Act: -0.0002

Data Index: 817563 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1170519 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0464. Min Act: -0.0002

Data Index: 698005 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0435. Min Act: -0.0002

Data Index: 897356 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1208478 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1290522 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0418. Min Act: -0.0002

Data Index: 846116 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0414. Min Act: -0.0002

Data Index: 227059 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1237834 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0403. Min Act: -0.0002

Data Index: 869041 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0402. Min Act: -0.0002

Data Index: 875045 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0410. Min Act: -0.0002

Data Index: 808934 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0393. Min Act: -0.0002

Data Index: 565423 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1100770 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0391. Min Act: -0.0002

Data Index: 8982 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0397. Min Act: -0.0002

Data Index: 13869 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0396. Min Act: -0.0002

Data Index: 49406 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0389. Min Act: -0.0002

Data Index: 362103 (C4 (Web Text))

Max Activating Token Index: 394