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

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

Neuron 549 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: 0.2421. Min Range: -0.2421

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1134180 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2284. Min Act: -0.0001

Data Index: 987709 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2237. Min Act: -0.0000

Data Index: 763346 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2421. Min Act: -0.0000

Data Index: 111556 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2331. Min Act: -0.0001

Data Index: 568019 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2269. Min Act: -0.0001

Data Index: 196981 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2175. Min Act: -0.0001

Data Index: 190403 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2100. Min Act: -0.0000

Data Index: 744851 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1912. Min Act: -0.0001

Data Index: 1294600 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1253398 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1776. Min Act: -0.0000

Data Index: 968555 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1030576 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1827. Min Act: -0.0000

Data Index: 374239 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1535. Min Act: -0.0000

Data Index: 756367 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1044316 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1124266 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1606. Min Act: -0.0001

Data Index: 584774 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1139984 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1523. Min Act: -0.0000

Data Index: 974155 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1733. Min Act: -0.0001

Data Index: 988128 (C4 (Web Text))

Max Activating Token Index: 816