Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0709. Min Range: -1.0709

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1845871 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9958. Min Act: -0.0000

Data Index: 958611 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1435121 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9376. Min Act: -0.0000

Data Index: 287606 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8281. Min Act: -0.0000

Data Index: 582860 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1842578 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8480. Min Act: -0.0000

Data Index: 109515 (The Pile)

Max Activating Token Index: 685

Text #7

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8310. Min Act: -0.0000

Data Index: 211014 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8270. Min Act: -0.0000

Data Index: 462566 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7692. Min Act: -0.0000

Data Index: 729671 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7823. Min Act: -0.0000

Data Index: 14645 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8048. Min Act: -0.0000

Data Index: 643565 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8027. Min Act: -0.0000

Data Index: 880303 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7600. Min Act: -0.0000

Data Index: 937464 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1072982 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7635. Min Act: -0.0000

Data Index: 7190 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7766. Min Act: -0.0000

Data Index: 656902 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1444730 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1946957 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1246387 (The Pile)

Max Activating Token Index: 237