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

Dataset: The Pile

Neuron 773 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: 1.1770. Min Range: -1.1770

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1931677 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.1770. Min Range: -1.1770

Max Act: 1.1170. Min Act: 0.0000

Data Index: 1414030 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 1.1770. Min Range: -1.1770

Max Act: 1.0459. Min Act: -0.0000

Data Index: 917326 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 1.1770. Min Range: -1.1770

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1426591 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8699. Min Act: 0.0000

Data Index: 1467302 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1835029 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9385. Min Act: -0.0000

Data Index: 609599 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8653. Min Act: -0.0000

Data Index: 84408 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9255. Min Act: -0.0000

Data Index: 946484 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8927. Min Act: -0.0000

Data Index: 783669 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1489665 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9164. Min Act: -0.0000

Data Index: 168973 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1471819 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1747895 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1694488 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8414. Min Act: -0.0000

Data Index: 739563 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9515. Min Act: -0.0000

Data Index: 173855 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9564. Min Act: -0.0000

Data Index: 201720 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1808735 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9360. Min Act: -0.0000

Data Index: 593239 (The Pile)

Max Activating Token Index: 439