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

Dataset: The Pile

Neuron 340 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: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1780497 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2089. Min Act: -0.0000

Data Index: 479413 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2015. Min Act: -0.0000

Data Index: 998193 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2020. Min Act: -0.0000

Data Index: 593068 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1610631 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1613. Min Act: -0.0000

Data Index: 431188 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1308622 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1739. Min Act: -0.0000

Data Index: 826782 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1608. Min Act: -0.0000

Data Index: 711617 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1619168 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1663. Min Act: -0.0000

Data Index: 935547 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1595. Min Act: -0.0000

Data Index: 249364 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1765. Min Act: -0.0000

Data Index: 772491 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1796589 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1736. Min Act: -0.0000

Data Index: 871258 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1650. Min Act: -0.0000

Data Index: 712306 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1729. Min Act: -0.0000

Data Index: 494045 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1625283 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1005021 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1583. Min Act: -0.0000

Data Index: 1384278 (The Pile)

Max Activating Token Index: 188