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

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

Neuron 2863 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2697. Min Act: -0.0000

Data Index: 61651 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2047. Min Act: 0.0000

Data Index: 254821 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2024. Min Act: 0.0000

Data Index: 622826 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1008223 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1974. Min Act: -0.0000

Data Index: 564575 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1812. Min Act: -0.0000

Data Index: 17479 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1707. Min Act: -0.0000

Data Index: 714895 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1702. Min Act: -0.0000

Data Index: 50896 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1732. Min Act: -0.0000

Data Index: 115628 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1719. Min Act: -0.0000

Data Index: 72268 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1684. Min Act: -0.0000

Data Index: 134595 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1797. Min Act: -0.0000

Data Index: 662585 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1625. Min Act: -0.0000

Data Index: 741940 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1656. Min Act: -0.0000

Data Index: 713068 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1011863 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1512. Min Act: -0.0000

Data Index: 664093 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1605. Min Act: -0.0000

Data Index: 960158 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1586. Min Act: -0.0000

Data Index: 809929 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1638. Min Act: -0.0000

Data Index: 893151 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1750. Min Act: -0.0000

Data Index: 960449 (C4 (Web Text))

Max Activating Token Index: 221