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

Dataset: The Pile

Neuron 3815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.4514. Min Act: -0.0000

Data Index: 1532121 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.8753. Min Act: -0.0000

Data Index: 1716551 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.3856. Min Act: -0.0000

Data Index: 533076 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.5582. Min Act: -0.0000

Data Index: 346694 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.3212. Min Act: -0.0000

Data Index: 772268 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.2947. Min Act: -0.0000

Data Index: 537952 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.1318. Min Act: -0.0000

Data Index: 1728427 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.2780. Min Act: -0.0000

Data Index: 180069 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.4229. Min Act: -0.0000

Data Index: 244000 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.2388. Min Act: -0.0000

Data Index: 509895 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.0171. Min Act: -0.0000

Data Index: 991960 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 5.4514. Min Range: -5.4514

Max Act: 3.8751. Min Act: -0.0000

Data Index: 1363594 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.1649. Min Act: -0.0000

Data Index: 554597 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.1699. Min Act: -0.0000

Data Index: 408618 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 5.4514. Min Range: -5.4514

Max Act: 3.7847. Min Act: -0.0000

Data Index: 1256712 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 5.4514. Min Range: -5.4514

Max Act: 4.0454. Min Act: -0.0000

Data Index: 1834459 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 5.4514. Min Range: -5.4514

Max Act: 3.7056. Min Act: -0.0000

Data Index: 1639510 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 5.4514. Min Range: -5.4514

Max Act: 3.8603. Min Act: -0.0000

Data Index: 16319 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 5.4514. Min Range: -5.4514

Max Act: 3.7927. Min Act: -0.0000

Data Index: 729544 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 5.4514. Min Range: -5.4514

Max Act: 3.9102. Min Act: -0.0000

Data Index: 739674 (The Pile)

Max Activating Token Index: 560