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

Dataset: The Pile

Neuron 864 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: 1.4666. Min Range: -1.4666

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1895429 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.4631. Min Act: -0.0000

Data Index: 899265 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1070498 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1627219 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1833641 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1951. Min Act: -0.0000

Data Index: 519905 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2357. Min Act: -0.0000

Data Index: 568637 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1288501 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2318. Min Act: -0.0000

Data Index: 23383 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3144. Min Act: -0.0000

Data Index: 1567758 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1129. Min Act: -0.0000

Data Index: 643482 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1501611 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1003798 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1644433 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1929328 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.9888. Min Act: -0.0000

Data Index: 442504 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0326. Min Act: -0.0000

Data Index: 969540 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1266785 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0978. Min Act: -0.0000

Data Index: 396962 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.9786. Min Act: -0.0000

Data Index: 854447 (The Pile)

Max Activating Token Index: 89