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

Dataset: The Pile

Neuron 3337 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: 1.1563. Min Range: -1.1563

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1898041 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1496938 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0672. Min Act: -0.0000

Data Index: 797632 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1556973 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1566427 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1467833 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9659. Min Act: -0.0000

Data Index: 417689 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9772. Min Act: -0.0000

Data Index: 669806 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8992. Min Act: -0.0000

Data Index: 714397 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8178. Min Act: -0.0000

Data Index: 230857 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1641626 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9358. Min Act: -0.0000

Data Index: 418316 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8703. Min Act: -0.0000

Data Index: 312575 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1651040 (The Pile)

Max Activating Token Index: 474

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1346696 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8579. Min Act: -0.0000

Data Index: 359894 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8466. Min Act: -0.0000

Data Index: 29846 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1709517 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1608106 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1969765 (The Pile)

Max Activating Token Index: 223