Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1856 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1210946 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1788. Min Act: -0.0002

Data Index: 125933 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1730. Min Act: -0.0002

Data Index: 1152811 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1719. Min Act: -0.0002

Data Index: 973876 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1701. Min Act: -0.0002

Data Index: 925144 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1674. Min Act: -0.0002

Data Index: 88032 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1623. Min Act: -0.0002

Data Index: 105491 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1665. Min Act: -0.0000

Data Index: 606978 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1611. Min Act: -0.0002

Data Index: 427526 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1667. Min Act: -0.0001

Data Index: 749559 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1678. Min Act: -0.0002

Data Index: 1081551 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1608. Min Act: -0.0002

Data Index: 640472 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1614. Min Act: -0.0002

Data Index: 970960 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1558. Min Act: -0.0000

Data Index: 735602 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1619. Min Act: -0.0002

Data Index: 810859 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1535. Min Act: -0.0002

Data Index: 900270 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1545. Min Act: -0.0002

Data Index: 196124 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1576. Min Act: -0.0001

Data Index: 797646 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1632. Min Act: -0.0001

Data Index: 429144 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1587. Min Act: -0.0002

Data Index: 288282 (C4 (Web Text))

Max Activating Token Index: 365