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

Dataset: The Pile

Neuron 59 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.6509. Min Act: -0.0000

Data Index: 1502470 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.5819. Min Act: -0.0000

Data Index: 606602 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.5858. Min Act: -0.0000

Data Index: 1747967 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1597825 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1115467 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.4166. Min Act: -0.0000

Data Index: 50511 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.4559. Min Act: -0.0000

Data Index: 530861 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.3066. Min Act: -0.0000

Data Index: 1103088 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.3034. Min Act: -0.0000

Data Index: 431254 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.2709. Min Act: -0.0000

Data Index: 222392 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.3196. Min Act: -0.0000

Data Index: 505713 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.2839. Min Act: -0.0000

Data Index: 611469 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1328662 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1597608 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1348520 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.3921. Min Act: -0.0000

Data Index: 972797 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1750928 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.2370. Min Act: -0.0000

Data Index: 64063 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.2482. Min Act: -0.0000

Data Index: 610797 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1444365 (The Pile)

Max Activating Token Index: 665