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

Dataset: The Pile

Neuron 631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2725. Min Range: -3.2725

Max Act: 3.2725. Min Act: -0.0000

Data Index: 1804640 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.6035. Min Act: -0.0000

Data Index: 1153741 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.3563. Min Act: -0.0001

Data Index: 1325618 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.0808. Min Act: -0.0000

Data Index: 1064726 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.1702. Min Act: -0.0000

Data Index: 1749633 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.9899. Min Act: -0.0000

Data Index: 1645099 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.0264. Min Act: -0.0000

Data Index: 829709 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.8137. Min Act: -0.0000

Data Index: 1762347 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.8607. Min Act: -0.0000

Data Index: 1500019 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.7896. Min Act: -0.0000

Data Index: 1851379 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.5947. Min Act: -0.0000

Data Index: 348978 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.7290. Min Act: -0.0000

Data Index: 1721047 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1885936 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1394065 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.7187. Min Act: -0.0000

Data Index: 1936350 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1811191 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1454359 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1469418 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.6556. Min Act: -0.0000

Data Index: 1194698 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 3.2725. Min Range: -3.2725

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1709099 (The Pile)

Max Activating Token Index: 672