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

Dataset: The Pile

Neuron 1759 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: 1.3873. Min Range: -1.3873

Max Act: 1.3873. Min Act: -0.0000

Data Index: 821118 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1856222 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1342816 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1641270 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1079885 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1340. Min Act: -0.0000

Data Index: 485095 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1227848 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1350429 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1255791 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1711173 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0393. Min Act: -0.0000

Data Index: 933951 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1155. Min Act: -0.0000

Data Index: 76510 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0494. Min Act: -0.0000

Data Index: 845309 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1121201 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1587790 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9615. Min Act: -0.0000

Data Index: 91790 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1939757 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1070631 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0397. Min Act: -0.0000

Data Index: 191291 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1815594 (The Pile)

Max Activating Token Index: 562