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

Dataset: The Pile

Neuron 4302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6756. Min Range: -3.6756

Max Act: 2.7561. Min Act: -0.0000

Data Index: 1449927 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.5759. Min Act: -0.0000

Data Index: 1734690 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.6756. Min Act: -0.0000

Data Index: 1266782 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.5177. Min Act: -0.0000

Data Index: 93328 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.5102. Min Act: -0.0000

Data Index: 1692627 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.3315. Min Act: -0.0000

Data Index: 973916 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.2645. Min Act: -0.0000

Data Index: 765358 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.3364. Min Act: -0.0000

Data Index: 679251 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.1475. Min Act: -0.0000

Data Index: 1902415 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.2921. Min Act: -0.0000

Data Index: 86406 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.2727. Min Act: -0.0000

Data Index: 1956325 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.2551. Min Act: -0.0000

Data Index: 260793 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.3137. Min Act: -0.0000

Data Index: 85351 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.0505. Min Act: -0.0000

Data Index: 6555 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.0582. Min Act: -0.0000

Data Index: 308472 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 3.6756. Min Range: -3.6756

Max Act: 2.8718. Min Act: -0.0000

Data Index: 233191 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 3.6756. Min Range: -3.6756

Max Act: 3.0233. Min Act: -0.0000

Data Index: 1828124 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 3.6756. Min Range: -3.6756

Max Act: 2.9978. Min Act: -0.0000

Data Index: 250587 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 3.6756. Min Range: -3.6756

Max Act: 2.9879. Min Act: -0.0000

Data Index: 1810394 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 3.6756. Min Range: -3.6756

Max Act: 2.8617. Min Act: -0.0000

Data Index: 37391 (The Pile)

Max Activating Token Index: 413