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

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

Neuron 5134 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: 1.6006. Min Range: -1.6006

Max Act: 1.6006. Min Act: -0.0000

Data Index: 226020 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.5181. Min Act: -0.0000

Data Index: 5473 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.3511. Min Act: -0.0000

Data Index: 886368 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.3802. Min Act: -0.0000

Data Index: 981772 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.2176. Min Act: -0.0000

Data Index: 346245 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1207649 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1306707 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1139487 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1751. Min Act: -0.0000

Data Index: 439498 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1655. Min Act: -0.0000

Data Index: 599698 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1115038 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1705. Min Act: -0.0000

Data Index: 574024 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1576. Min Act: -0.0000

Data Index: 774845 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1501. Min Act: -0.0000

Data Index: 920786 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.1129. Min Act: -0.0000

Data Index: 494094 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.0624. Min Act: -0.0000

Data Index: 989137 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.0907. Min Act: -0.0000

Data Index: 181525 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.0897. Min Act: -0.0000

Data Index: 215855 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.0843. Min Act: -0.0000

Data Index: 777674 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.6006. Min Range: -1.6006

Max Act: 1.0502. Min Act: -0.0000

Data Index: 976606 (C4 (Web Text))

Max Activating Token Index: 78