Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1563787 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1934. Min Act: -0.0000

Data Index: 705245 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1968. Min Act: -0.0000

Data Index: 936929 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1277717 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1445558 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1647. Min Act: -0.0000

Data Index: 63829 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1720. Min Act: -0.0000

Data Index: 639592 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1713. Min Act: -0.0000

Data Index: 368751 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1458683 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1658. Min Act: -0.0000

Data Index: 338926 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1587. Min Act: -0.0000

Data Index: 167739 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1716. Min Act: -0.0000

Data Index: 239445 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1107858 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1381677 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1954196 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1594895 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1372111 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1985197 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1618. Min Act: -0.0000

Data Index: 855366 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1376033 (The Pile)

Max Activating Token Index: 549