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

Dataset: The Pile

Neuron 3759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.2118. Min Act: -0.0000

Data Index: 571256 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.2586. Min Act: -0.0000

Data Index: 201121 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.1900. Min Act: -0.0000

Data Index: 126220 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1093152 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0564. Min Act: -0.0000

Data Index: 483061 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.3380. Min Act: -0.0000

Data Index: 13254 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0844. Min Act: -0.0000

Data Index: 549437 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1943741 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1024004 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1719565 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9735. Min Act: -0.0000

Data Index: 895705 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1906353 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0405. Min Act: -0.0000

Data Index: 46207 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1767816 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9755. Min Act: -0.0000

Data Index: 354655 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1523101 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1784285 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1751305 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8388. Min Act: -0.0000

Data Index: 215434 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9694. Min Act: -0.0000

Data Index: 340505 (The Pile)

Max Activating Token Index: 95