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

Dataset: The Pile

Neuron 3018 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: 1.2802. Min Range: -1.2802

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1146998 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.2802. Min Act: -0.0000

Data Index: 782359 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1661. Min Act: -0.0000

Data Index: 434796 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1655495 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0570. Min Act: -0.0000

Data Index: 51686 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0516. Min Act: -0.0000

Data Index: 578817 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1336179 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1391. Min Act: -0.0000

Data Index: 557105 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1343785 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1494. Min Act: -0.0000

Data Index: 728576 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0219. Min Act: -0.0000

Data Index: 578612 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1198835 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0658. Min Act: -0.0000

Data Index: 481269 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1654163 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0329. Min Act: -0.0000

Data Index: 547009 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1765855 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9162. Min Act: -0.0000

Data Index: 13878 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1053584 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1675523 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8956. Min Act: -0.0000

Data Index: 862978 (The Pile)

Max Activating Token Index: 916