Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2605. Min Act: -0.0000

Data Index: 848893 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1410629 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1915. Min Act: -0.0001

Data Index: 409584 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1412292 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1430583 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1510514 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1821. Min Act: -0.0001

Data Index: 760448 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1785. Min Act: -0.0000

Data Index: 35627 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1989. Min Act: 0.0000

Data Index: 688495 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1774. Min Act: -0.0001

Data Index: 566975 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1649. Min Act: -0.0000

Data Index: 635516 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2030. Min Act: 0.0000

Data Index: 591965 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1633. Min Act: -0.0000

Data Index: 136554 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1521441 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1550719 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1955. Min Act: -0.0000

Data Index: 935220 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1916371 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1840. Min Act: -0.0000

Data Index: 944252 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1056383 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1694. Min Act: -0.0000

Data Index: 432958 (The Pile)

Max Activating Token Index: 673