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

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

Neuron 3589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1837. Min Act: 0.0001

Data Index: 1369284 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1893. Min Act: -0.0001

Data Index: 945827 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1878. Min Act: -0.0000

Data Index: 936879 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1312498 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1917. Min Act: -0.0001

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1783. Min Act: -0.0000

Data Index: 824777 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1625341 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1649. Min Act: -0.0001

Data Index: 409316 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1575447 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1736. Min Act: -0.0001

Data Index: 743283 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1315785 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1280291 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1328732 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1203266 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1489405 (Python Code)

Max Activating Token Index: 687

Text #15

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1558016 (Python Code)

Max Activating Token Index: 748

Text #16

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1393935 (Python Code)

Max Activating Token Index: 845

Text #17

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1583629 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1658. Min Act: -0.0000

Data Index: 247813 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1651591 (Python Code)

Max Activating Token Index: 171