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

Dataset: The Pile

Neuron 3433 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1692865 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1985017 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1533009 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1737198 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1403294 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1818526 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0717. Min Act: -0.0000

Data Index: 599322 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0660. Min Act: -0.0000

Data Index: 459548 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0644. Min Act: -0.0000

Data Index: 598374 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1022715 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1539652 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1970755 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1459139 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1254398 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1434412 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1226264 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0636. Min Act: -0.0000

Data Index: 222942 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0633. Min Act: -0.0000

Data Index: 234204 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1590711 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0652. Min Act: -0.0000

Data Index: 670998 (The Pile)

Max Activating Token Index: 511