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

Dataset: The Pile

Neuron 1664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.5733. Min Act: -0.0000

Data Index: 652663 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.4665. Min Act: -0.0000

Data Index: 719808 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.4538. Min Act: -0.0000

Data Index: 261012 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.5355. Min Act: -0.0000

Data Index: 1113747 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1211696 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1800460 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1734. Min Act: -0.0000

Data Index: 20826 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1843. Min Act: -0.0000

Data Index: 948540 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1261006 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1632760 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1014558 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0606. Min Act: -0.0000

Data Index: 652361 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1355032 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1662339 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0986. Min Act: -0.0000

Data Index: 346856 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1007. Min Act: -0.0000

Data Index: 208709 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1926620 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1803700 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1704666 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1402260 (The Pile)

Max Activating Token Index: 558