Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4620 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1115342 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0409. Min Act: -0.0002

Data Index: 596478 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0397. Min Act: -0.0002

Data Index: 710776 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1055852 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0368. Min Act: -0.0002

Data Index: 854302 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0359. Min Act: -0.0002

Data Index: 785001 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0386. Min Act: -0.0002

Data Index: 288124 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1066905 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0394. Min Act: -0.0002

Data Index: 428738 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1230196 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0361. Min Act: -0.0002

Data Index: 216905 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0255. Min Act: -0.0002

Data Index: 770145 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0372. Min Act: -0.0002

Data Index: 582019 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0372. Min Act: -0.0002

Data Index: 974765 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0369. Min Act: -0.0002

Data Index: 704595 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1031090 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0352. Min Act: -0.0002

Data Index: 878968 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1075502 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0350. Min Act: -0.0002

Data Index: 45236 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0347. Min Act: -0.0002

Data Index: 333753 (C4 (Web Text))

Max Activating Token Index: 831