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

Dataset: The Pile

Neuron 431 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: 1.6493. Min Range: -1.6493

Max Act: 1.6493. Min Act: -0.0000

Data Index: 326423 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1214746 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4554. Min Act: -0.0000

Data Index: 1087787 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4110. Min Act: -0.0000

Data Index: 828303 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.3343. Min Act: -0.0000

Data Index: 1390886 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.2973. Min Act: -0.0000

Data Index: 550232 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1272480 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1213825 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.1725. Min Act: -0.0000

Data Index: 812080 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1271695 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1766586 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1398500 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1515616 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.1079. Min Act: -0.0000

Data Index: 673997 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.0822. Min Act: -0.0000

Data Index: 908702 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1557794 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.6493. Min Range: -1.6493

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1631354 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1927020 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1036003 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.0104. Min Act: -0.0000

Data Index: 778743 (The Pile)

Max Activating Token Index: 372