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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 13 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.2011. Min Act: -0.0002

Data Index: 432727 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.2040. Min Act: -0.0002

Data Index: 1120204 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1852. Min Act: -0.0002

Data Index: 1529627 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1777. Min Act: -0.0002

Data Index: 1555135 (Python Code)

Max Activating Token Index: 497

Text #4

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1784. Min Act: -0.0003

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1961. Min Act: -0.0002

Data Index: 1490178 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1660. Min Act: -0.0002

Data Index: 280336 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1737. Min Act: -0.0002

Data Index: 192352 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1719. Min Act: -0.0002

Data Index: 421318 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1827. Min Act: -0.0002

Data Index: 499704 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1729. Min Act: -0.0003

Data Index: 1153040 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1661. Min Act: -0.0002

Data Index: 1647707 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1766. Min Act: -0.0002

Data Index: 1378766 (Python Code)

Max Activating Token Index: 573

Text #13

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1862. Min Act: -0.0002

Data Index: 905468 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1690. Min Act: -0.0002

Data Index: 1363014 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1422582 (Python Code)

Max Activating Token Index: 810

Text #16

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1682. Min Act: -0.0002

Data Index: 1489519 (Python Code)

Max Activating Token Index: 490

Text #17

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1626. Min Act: -0.0002

Data Index: 1484569 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1631. Min Act: -0.0002

Data Index: 1568486 (Python Code)

Max Activating Token Index: 490

Text #19

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1662. Min Act: -0.0002

Data Index: 1402198 (Python Code)

Max Activating Token Index: 121