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

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

Neuron 2686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1031990 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3199. Min Act: -0.0000

Data Index: 714340 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2255. Min Act: -0.0000

Data Index: 933455 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2148. Min Act: -0.0000

Data Index: 765694 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2025. Min Act: -0.0000

Data Index: 689310 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1274360 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1910. Min Act: -0.0000

Data Index: 491554 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1072674 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1873. Min Act: -0.0000

Data Index: 341833 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1850. Min Act: -0.0000

Data Index: 180427 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1758. Min Act: -0.0000

Data Index: 303677 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1550468 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1715. Min Act: -0.0000

Data Index: 704150 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1754. Min Act: -0.0000

Data Index: 106598 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1062126 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1595. Min Act: -0.0000

Data Index: 344410 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1900. Min Act: -0.0000

Data Index: 41029 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1718. Min Act: -0.0000

Data Index: 298226 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1632. Min Act: -0.0000

Data Index: 432020 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1260582 (C4 (Web Text))

Max Activating Token Index: 441