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

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

Neuron 1636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2428. Min Act: -0.0000

Data Index: 574161 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1107973 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1894. Min Act: -0.0000

Data Index: 81907 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1882. Min Act: -0.0000

Data Index: 710880 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1772. Min Act: -0.0000

Data Index: 350295 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1034072 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1629. Min Act: -0.0000

Data Index: 371291 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1680. Min Act: -0.0000

Data Index: 662292 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1786. Min Act: -0.0000

Data Index: 813272 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1709. Min Act: -0.0000

Data Index: 61143 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1632. Min Act: -0.0000

Data Index: 562333 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1588. Min Act: -0.0000

Data Index: 731842 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1594. Min Act: -0.0000

Data Index: 396351 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1583. Min Act: -0.0000

Data Index: 458979 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1249957 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1224280 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1603. Min Act: -0.0000

Data Index: 499447 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1655. Min Act: -0.0000

Data Index: 101967 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1304501 (C4 (Web Text))

Max Activating Token Index: 72