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

Dataset: The Pile

Neuron 903 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: 1.2796. Min Range: -1.2796

Max Act: 1.2796. Min Act: -0.0000

Data Index: 394808 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0820. Min Act: -0.0000

Data Index: 1519548 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9888. Min Act: -0.0000

Data Index: 766973 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1461859 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0080. Min Act: -0.0000

Data Index: 340898 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0135. Min Act: -0.0000

Data Index: 593799 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1674197 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1867521 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1932635 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9538. Min Act: -0.0000

Data Index: 714500 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9706. Min Act: -0.0000

Data Index: 493932 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9676. Min Act: -0.0000

Data Index: 159849 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1679885 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1246389 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1281945 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0269. Min Act: -0.0000

Data Index: 789030 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1047995 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8895. Min Act: -0.0000

Data Index: 101949 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9584. Min Act: -0.0000

Data Index: 676967 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8257. Min Act: -0.0000

Data Index: 440275 (The Pile)

Max Activating Token Index: 229