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

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

Neuron 1539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4923. Min Act: -0.0000

Data Index: 756024 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.3659. Min Act: -0.0000

Data Index: 351521 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2667. Min Act: -0.0000

Data Index: 614782 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2872. Min Act: -0.0000

Data Index: 247901 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2051. Min Act: -0.0000

Data Index: 176677 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1853. Min Act: -0.0000

Data Index: 691397 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2024. Min Act: -0.0000

Data Index: 363328 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1041753 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1133162 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2438. Min Act: -0.0000

Data Index: 946049 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2895. Min Act: -0.0000

Data Index: 245045 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1160032 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2743. Min Act: -0.0000

Data Index: 214460 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.3066. Min Act: -0.0000

Data Index: 2018 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1712. Min Act: -0.0000

Data Index: 86268 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1096040 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1066022 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1074821 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1706. Min Act: -0.0000

Data Index: 777762 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2636. Min Act: -0.0000

Data Index: 1195663 (C4 (Web Text))

Max Activating Token Index: 654