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

Dataset: The Pile

Neuron 4130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.9789. Min Act: 0.0000

Data Index: 105802 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1273299 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.6753. Min Act: -0.0000

Data Index: 834719 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.4931. Min Act: -0.0000

Data Index: 848104 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.6448. Min Act: -0.0000

Data Index: 1966730 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.4386. Min Act: -0.0000

Data Index: 657955 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.3504. Min Act: -0.0000

Data Index: 847791 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1846811 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.3960. Min Act: -0.0000

Data Index: 66396 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1186656 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.3144. Min Act: -0.0000

Data Index: 30721 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1802237 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2151. Min Act: -0.0000

Data Index: 38743 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1342389 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1634723 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1546589 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2786. Min Act: -0.0000

Data Index: 1685657 (The Pile)

Max Activating Token Index: 543

Text #17

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1481456 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.2833. Min Act: -0.0000

Data Index: 94815 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 1.9789. Min Range: -1.9789

Max Act: 1.1948. Min Act: -0.0000

Data Index: 768227 (The Pile)

Max Activating Token Index: 636