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

Dataset: The Pile

Neuron 1462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1146818 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6039. Min Act: -0.0000

Data Index: 501383 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1317597 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1428521 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4948. Min Act: -0.0000

Data Index: 544411 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1403255 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1291310 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5144. Min Act: -0.0000

Data Index: 621529 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5557. Min Act: -0.0000

Data Index: 993507 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5220. Min Act: -0.0000

Data Index: 406896 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5279. Min Act: -0.0000

Data Index: 569458 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5383. Min Act: -0.0000

Data Index: 708916 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1759070 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1265444 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1683197 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5709. Min Act: -0.0000

Data Index: 709188 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5612. Min Act: -0.0000

Data Index: 562766 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1541324 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4360. Min Act: -0.0000

Data Index: 223473 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1740030 (The Pile)

Max Activating Token Index: 578