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

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

Neuron 5381 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.3730. Min Act: -0.0000

Data Index: 229821 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.3293. Min Act: -0.0000

Data Index: 77393 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.3210. Min Act: -0.0000

Data Index: 886520 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.2323. Min Act: -0.0000

Data Index: 18668 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1929. Min Act: -0.0000

Data Index: 807393 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1657. Min Act: -0.0000

Data Index: 278349 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1582790 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1437034 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1755. Min Act: -0.0000

Data Index: 584090 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1511. Min Act: -0.0000

Data Index: 587932 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1684. Min Act: -0.0000

Data Index: 985998 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1646388 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1477751 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1642. Min Act: -0.0000

Data Index: 164630 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1588. Min Act: -0.0000

Data Index: 635807 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1530. Min Act: -0.0000

Data Index: 426608 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1573. Min Act: -0.0000

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1585. Min Act: -0.0000

Data Index: 466494 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1627. Min Act: -0.0000

Data Index: 233454 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.3730. Min Range: -0.3730

Max Act: 0.1419. Min Act: -0.0000

Data Index: 7250 (C4 (Web Text))

Max Activating Token Index: 64