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

Dataset: The Pile

Neuron 4135 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: 1.5048. Min Range: -1.5048

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1974801 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.4324. Min Act: -0.0000

Data Index: 1228311 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.3519. Min Act: -0.0000

Data Index: 630753 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1285271 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1676769 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2831. Min Act: -0.0000

Data Index: 96489 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1935. Min Act: -0.0000

Data Index: 924560 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2614. Min Act: -0.0000

Data Index: 646133 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2388. Min Act: -0.0000

Data Index: 736758 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1954. Min Act: -0.0000

Data Index: 653989 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1574. Min Act: -0.0000

Data Index: 139902 (The Pile)

Max Activating Token Index: 244

Text #11

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1608. Min Act: -0.0000

Data Index: 451725 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1490929 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1736459 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1651907 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2540. Min Act: -0.0000

Data Index: 1156909 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1881. Min Act: -0.0000

Data Index: 794807 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1372426 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1233596 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2070. Min Act: -0.0000

Data Index: 777344 (The Pile)

Max Activating Token Index: 84