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

Dataset: The Pile

Neuron 409 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: 1.4542. Min Range: -1.4542

Max Act: 1.4542. Min Act: -0.0000

Data Index: 425591 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2189. Min Act: -0.0000

Data Index: 199062 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1742309 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1096. Min Act: -0.0000

Data Index: 971228 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1617878 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1832. Min Act: -0.0000

Data Index: 418935 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1734158 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1695324 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1267773 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1916220 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1117795 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1698. Min Act: -0.0000

Data Index: 990763 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0658. Min Act: -0.0000

Data Index: 160123 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 1.4542. Min Range: -1.4542

Max Act: 0.9668. Min Act: -0.0000

Data Index: 655246 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0433. Min Act: -0.0000

Data Index: 359458 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1050120 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 1.4542. Min Range: -1.4542

Max Act: 0.9923. Min Act: -0.0000

Data Index: 743961 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 1.4542. Min Range: -1.4542

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1249668 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.4542. Min Range: -1.4542

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1033440 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 1.4542. Min Range: -1.4542

Max Act: 0.9418. Min Act: -0.0000

Data Index: 238929 (The Pile)

Max Activating Token Index: 378