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

Dataset: The Pile

Neuron 4241 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: 0.0001

Data Index: 438466 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0753. Min Act: 0.0001

Data Index: 1342553 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1382304 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1614545 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1526797 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0652. Min Act: -0.0000

Data Index: 629224 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1059114 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1457019 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0621. Min Act: -0.0000

Data Index: 157571 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1426107 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1126629 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0594. Min Act: -0.0000

Data Index: 42899 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0581. Min Act: -0.0000

Data Index: 211686 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0581. Min Act: -0.0000

Data Index: 873424 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0574. Min Act: -0.0000

Data Index: 903461 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1742032 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0563. Min Act: -0.0000

Data Index: 35121 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0564. Min Act: -0.0000

Data Index: 841927 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1131454 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1122534 (The Pile)

Max Activating Token Index: 658