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

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

Neuron 523 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0002

Data Index: 23973 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0505. Min Act: -0.0002

Data Index: 440618 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0468. Min Act: -0.0002

Data Index: 737657 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1145926 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0408. Min Act: -0.0002

Data Index: 164086 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1026363 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1317537 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0408. Min Act: -0.0002

Data Index: 165955 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0394. Min Act: -0.0002

Data Index: 213258 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0390. Min Act: -0.0002

Data Index: 123439 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1328012 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0374. Min Act: -0.0002

Data Index: 730612 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1070885 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0390. Min Act: -0.0002

Data Index: 492723 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0381. Min Act: -0.0002

Data Index: 751539 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1276969 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0374. Min Act: -0.0002

Data Index: 283329 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0376. Min Act: -0.0002

Data Index: 838109 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0374. Min Act: -0.0002

Data Index: 707940 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0366. Min Act: -0.0002

Data Index: 928361 (C4 (Web Text))

Max Activating Token Index: 645