Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2400 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1174759 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1282892 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0467. Min Act: -0.0003

Data Index: 460242 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0439. Min Act: -0.0003

Data Index: 807945 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0410. Min Act: -0.0003

Data Index: 214503 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0397. Min Act: -0.0003

Data Index: 873872 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0398. Min Act: -0.0003

Data Index: 95534 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0400. Min Act: -0.0003

Data Index: 903891 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1302313 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0397. Min Act: -0.0003

Data Index: 733236 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0392. Min Act: -0.0003

Data Index: 760654 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0374. Min Act: -0.0003

Data Index: 98676 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0387. Min Act: -0.0003

Data Index: 220834 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0378. Min Act: -0.0003

Data Index: 660942 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0377. Min Act: -0.0003

Data Index: 397581 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1134966 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0394. Min Act: -0.0003

Data Index: 810299 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0372. Min Act: -0.0003

Data Index: 394567 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1047028 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0368. Min Act: -0.0003

Data Index: 250272 (C4 (Web Text))

Max Activating Token Index: 17