Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1953 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1949. Min Act: -0.0000

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1028828 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1991. Min Act: -0.0001

Data Index: 530238 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.2014. Min Act: -0.0000

Data Index: 787601 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1883. Min Act: -0.0000

Data Index: 555855 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1117497 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1261392 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1750. Min Act: -0.0001

Data Index: 346982 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1125435 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1625. Min Act: -0.0000

Data Index: 980270 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1635. Min Act: -0.0001

Data Index: 890772 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1683. Min Act: -0.0000

Data Index: 32440 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1495. Min Act: -0.0000

Data Index: 341104 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1444. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1103438 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1465. Min Act: -0.0001

Data Index: 177848 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1464. Min Act: -0.0000

Data Index: 739105 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1485. Min Act: -0.0000

Data Index: 799644 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1417. Min Act: -0.0000

Data Index: 360513 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1471. Min Act: -0.0000

Data Index: 469348 (C4 (Web Text))

Max Activating Token Index: 423