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

Dataset: The Pile

Neuron 4808 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: 0.2622. Min Range: -0.2622

Max Act: 0.2622. Min Act: -0.0000

Data Index: 901338 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2520. Min Act: -0.0000

Data Index: 47943 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1438830 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1467766 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2039. Min Act: -0.0000

Data Index: 681848 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1974861 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1913587 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1464575 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1674070 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1833. Min Act: -0.0000

Data Index: 398517 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1831. Min Act: -0.0000

Data Index: 759879 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1878. Min Act: -0.0000

Data Index: 609830 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1819338 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1602. Min Act: -0.0000

Data Index: 357630 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1825605 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1606. Min Act: -0.0000

Data Index: 626200 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1715. Min Act: -0.0000

Data Index: 872062 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1569513 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1908063 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1303443 (The Pile)

Max Activating Token Index: 190