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

Dataset: The Pile

Neuron 3452 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: 0.2392. Min Range: -0.2392

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1768414 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1824578 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1845844 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1682. Min Act: -0.0000

Data Index: 49784 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1925. Min Act: -0.0000

Data Index: 972597 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1511951 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1827874 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1785913 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1660244 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1171370 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1800. Min Act: -0.0000

Data Index: 422595 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1236209 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1675. Min Act: -0.0000

Data Index: 527034 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1778220 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1119675 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1504691 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1538123 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1385308 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1449. Min Act: -0.0000

Data Index: 861174 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1433446 (The Pile)

Max Activating Token Index: 1006