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

Dataset: The Pile

Neuron 4821 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.1502. Min Act: -0.0000

Data Index: 1299812 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1627107 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.0816. Min Act: -0.0000

Data Index: 925026 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.0799. Min Act: -0.0000

Data Index: 603648 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.0645. Min Act: -0.0000

Data Index: 690858 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1731523 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1317808 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.0147. Min Act: -0.0000

Data Index: 261230 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9666. Min Act: -0.0000

Data Index: 583444 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9271. Min Act: -0.0000

Data Index: 610773 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9907. Min Act: -0.0000

Data Index: 125762 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9804. Min Act: -0.0000

Data Index: 123008 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 1.1502. Min Range: -1.1502

Max Act: 1.0117. Min Act: -0.0000

Data Index: 260704 (The Pile)

Max Activating Token Index: 251

Text #13

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9157. Min Act: -0.0000

Data Index: 274761 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.8500. Min Act: -0.0000

Data Index: 777962 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1040381 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9174. Min Act: -0.0000

Data Index: 680322 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9034. Min Act: -0.0000

Data Index: 919744 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1056909 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.1502. Min Range: -1.1502

Max Act: 0.8768. Min Act: -0.0000

Data Index: 924529 (The Pile)

Max Activating Token Index: 208