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

Dataset: The Pile

Neuron 4227 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: 0.6814. Min Range: -0.6814

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1420913 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6204. Min Act: -0.0000

Data Index: 190232 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6214. Min Act: -0.0000

Data Index: 143081 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6224. Min Act: -0.0000

Data Index: 419200 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6045. Min Act: -0.0000

Data Index: 399997 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5985. Min Act: -0.0000

Data Index: 536294 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1410687 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6384. Min Act: -0.0000

Data Index: 613998 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5845. Min Act: -0.0000

Data Index: 678286 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1452657 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1670275 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5775. Min Act: -0.0000

Data Index: 800925 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5816. Min Act: -0.0000

Data Index: 531460 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1948917 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5760. Min Act: -0.0000

Data Index: 798516 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5764. Min Act: -0.0000

Data Index: 458006 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1577978 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1865796 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1640663 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1880027 (The Pile)

Max Activating Token Index: 219