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

Dataset: The Pile

Neuron 1717 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1632892 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0729. Min Act: 0.0000

Data Index: 984706 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0696. Min Act: -0.0000

Data Index: 670204 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1681816 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0655. Min Act: -0.0000

Data Index: 409259 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0622. Min Act: -0.0000

Data Index: 84535 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0633. Min Act: -0.0000

Data Index: 381459 (The Pile)

Max Activating Token Index: 801

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1326766 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0607. Min Act: -0.0000

Data Index: 86395 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0541. Min Act: -0.0000

Data Index: 515401 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1892740 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0616. Min Act: -0.0000

Data Index: 183795 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1143681 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0597. Min Act: -0.0000

Data Index: 15338 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1159878 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0505. Min Act: -0.0000

Data Index: 812348 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0573. Min Act: -0.0000

Data Index: 475652 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0638. Min Act: -0.0000

Data Index: 80923 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1810121 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1162868 (The Pile)

Max Activating Token Index: 736