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

Dataset: The Pile

Neuron 2058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9653. Min Act: -0.0000

Data Index: 876371 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0248. Min Act: -0.0000

Data Index: 240975 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1117203 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1973420 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0399. Min Act: -0.0000

Data Index: 684048 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1881279 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9823. Min Act: -0.0000

Data Index: 937529 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1312279 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1205588 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1534117 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0067. Min Act: -0.0000

Data Index: 655974 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8682. Min Act: -0.0000

Data Index: 505200 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9069. Min Act: -0.0000

Data Index: 708531 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1612271 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8780. Min Act: -0.0000

Data Index: 520561 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1961421 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1925240 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1273355 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8976. Min Act: -0.0000

Data Index: 768185 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8903. Min Act: -0.0000

Data Index: 86330 (The Pile)

Max Activating Token Index: 492