Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2199 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1524496 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2685. Min Act: -0.0000

Data Index: 945926 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2377. Min Act: -0.0000

Data Index: 708378 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2137. Min Act: -0.0000

Data Index: 129106 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2002. Min Act: -0.0000

Data Index: 596736 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1988. Min Act: -0.0000

Data Index: 65878 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1954. Min Act: -0.0000

Data Index: 445114 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1924. Min Act: -0.0000

Data Index: 89997 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1267978 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1712. Min Act: -0.0000

Data Index: 123212 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1031265 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1466786 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1833. Min Act: -0.0000

Data Index: 851510 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1847. Min Act: 0.0000

Data Index: 126047 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1788. Min Act: -0.0000

Data Index: 427796 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1710. Min Act: -0.0000

Data Index: 666066 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1593. Min Act: -0.0000

Data Index: 789710 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1652. Min Act: -0.0000

Data Index: 150289 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1692. Min Act: 0.0000

Data Index: 1100533 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1335588 (C4 (Web Text))

Max Activating Token Index: 555