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

Dataset: The Pile

Neuron 252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1476915 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6575. Min Act: -0.0000

Data Index: 798400 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5215. Min Act: 0.0000

Data Index: 870483 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1405465 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.4118. Min Act: -0.0000

Data Index: 801258 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3605. Min Act: -0.0000

Data Index: 636607 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3810. Min Act: 0.0000

Data Index: 1489165 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3739. Min Act: -0.0000

Data Index: 239766 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1958886 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1066650 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3656. Min Act: -0.0001

Data Index: 1683802 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1042282 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1696849 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3614. Min Act: -0.0001

Data Index: 1954326 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3476. Min Act: -0.0000

Data Index: 571187 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3642. Min Act: -0.0000

Data Index: 346351 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.2785. Min Act: -0.0000

Data Index: 680088 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1960658 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3478. Min Act: -0.0000

Data Index: 387549 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.3828. Min Act: -0.0000

Data Index: 479082 (The Pile)

Max Activating Token Index: 721