Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1447 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2219. Min Act: -0.0000

Data Index: 870414 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1077155 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1250900 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2041. Min Act: -0.0001

Data Index: 432577 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2017. Min Act: -0.0001

Data Index: 146068 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1821. Min Act: -0.0000

Data Index: 933845 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1886. Min Act: -0.0001

Data Index: 542913 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1341406 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1877. Min Act: -0.0000

Data Index: 667124 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1727. Min Act: -0.0000

Data Index: 733128 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1708. Min Act: -0.0001

Data Index: 282517 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1854. Min Act: -0.0001

Data Index: 409433 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1735. Min Act: -0.0000

Data Index: 829777 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1741. Min Act: -0.0000

Data Index: 510010 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1040708 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1679. Min Act: -0.0000

Data Index: 733123 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1710. Min Act: -0.0000

Data Index: 928468 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1653. Min Act: -0.0000

Data Index: 364628 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1597. Min Act: -0.0000

Data Index: 651583 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1719. Min Act: -0.0000

Data Index: 22213 (C4 (Web Text))

Max Activating Token Index: 275