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

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

Neuron 1721 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: 0.1988. Min Range: -0.1988

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1354267 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1912. Min Act: -0.0001

Data Index: 900050 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1988. Min Act: -0.0000

Data Index: 847186 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1036048 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1874. Min Act: -0.0001

Data Index: 368614 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1810. Min Act: -0.0000

Data Index: 665644 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1866. Min Act: -0.0000

Data Index: 668189 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1030435 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1597. Min Act: -0.0001

Data Index: 945237 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1717. Min Act: -0.0000

Data Index: 574229 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1182738 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1753. Min Act: -0.0000

Data Index: 228575 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1695. Min Act: -0.0001

Data Index: 167825 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1664. Min Act: -0.0000

Data Index: 441050 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1835. Min Act: -0.0000

Data Index: 586208 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1590. Min Act: -0.0001

Data Index: 831557 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1720. Min Act: -0.0000

Data Index: 121059 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1826. Min Act: -0.0001

Data Index: 78821 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1615365 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1690. Min Act: -0.0001

Data Index: 683108 (C4 (Web Text))

Max Activating Token Index: 745