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

Dataset: The Pile

Neuron 178 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3645. Min Act: -0.0000

Data Index: 37773 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3508. Min Act: -0.0000

Data Index: 668952 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1082651 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1806078 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1852502 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2902. Min Act: -0.0000

Data Index: 14291 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1602145 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1532812 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1154046 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2614. Min Act: -0.0000

Data Index: 351614 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1111333 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2676. Min Act: -0.0000

Data Index: 683952 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2529. Min Act: -0.0000

Data Index: 556904 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2661. Min Act: -0.0000

Data Index: 51966 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1587837 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1236664 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1216879 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1176093 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2615. Min Act: -0.0000

Data Index: 73789 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1928279 (The Pile)

Max Activating Token Index: 154