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

Dataset: The Pile

Neuron 4529 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1928602 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3782. Min Act: -0.0000

Data Index: 392449 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1077016 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2923. Min Act: -0.0000

Data Index: 626163 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1845872 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1811866 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2890. Min Act: -0.0000

Data Index: 635071 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1291584 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2741. Min Act: -0.0000

Data Index: 863475 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1298272 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1824956 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2883. Min Act: -0.0000

Data Index: 686607 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2234. Min Act: -0.0000

Data Index: 482611 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2177. Min Act: 0.0000

Data Index: 1222087 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1833562 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.1902. Min Act: 0.0000

Data Index: 1741957 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2149. Min Act: -0.0000

Data Index: 471763 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.1783. Min Act: -0.0000

Data Index: 694986 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.1955. Min Act: 0.0000

Data Index: 646322 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.1964. Min Act: 0.0000

Data Index: 1914487 (The Pile)

Max Activating Token Index: 271