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

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

Neuron 5262 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.5546. Min Act: -0.0000

Data Index: 112533 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.5169. Min Act: -0.0000

Data Index: 949463 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.3751. Min Act: -0.0000

Data Index: 131667 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1758. Min Act: -0.0000

Data Index: 647248 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.2150. Min Act: -0.0000

Data Index: 784203 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.3027. Min Act: 0.0001

Data Index: 1282729 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1856. Min Act: -0.0000

Data Index: 855833 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1900. Min Act: 0.0001

Data Index: 156557 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1705. Min Act: -0.0000

Data Index: 839291 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1283847 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1709. Min Act: 0.0001

Data Index: 707880 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.0585. Min Act: 0.0001

Data Index: 92183 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1195491 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.5546. Min Range: -1.5546

Max Act: 0.9737. Min Act: 0.0000

Data Index: 502932 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.0298. Min Act: -0.0000

Data Index: 101189 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.5546. Min Range: -1.5546

Max Act: 1.0021. Min Act: -0.0000

Data Index: 808125 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.5546. Min Range: -1.5546

Max Act: 0.9343. Min Act: -0.0000

Data Index: 86620 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.5546. Min Range: -1.5546

Max Act: 0.9798. Min Act: -0.0000

Data Index: 938884 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 1.5546. Min Range: -1.5546

Max Act: 0.9628. Min Act: -0.0000

Data Index: 132873 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.5546. Min Range: -1.5546

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1228685 (C4 (Web Text))

Max Activating Token Index: 799