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

Dataset: The Pile

Neuron 1485 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4860. Min Act: -0.0000

Data Index: 107147 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4295. Min Act: -0.0000

Data Index: 240570 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1349558 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1836055 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1304994 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1421848 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1677017 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3100. Min Act: -0.0000

Data Index: 24695 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1208661 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1507079 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2753. Min Act: -0.0000

Data Index: 305342 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1121190 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2800. Min Act: -0.0000

Data Index: 123239 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1270615 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2629. Min Act: -0.0000

Data Index: 616962 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1761152 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2567. Min Act: 0.0000

Data Index: 1963905 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2716. Min Act: -0.0000

Data Index: 650867 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2820. Min Act: 0.0000

Data Index: 1120836 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2969. Min Act: -0.0000

Data Index: 964568 (The Pile)

Max Activating Token Index: 948