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

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

Neuron 3214 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.3563. Min Act: -0.0000

Data Index: 332548 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.2456. Min Act: -0.0000

Data Index: 273115 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1995. Min Act: -0.0000

Data Index: 554403 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1893. Min Act: -0.0000

Data Index: 265829 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1277420 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1806. Min Act: -0.0000

Data Index: 674826 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1351309 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1884. Min Act: -0.0000

Data Index: 605849 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1311546 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1868. Min Act: -0.0000

Data Index: 491174 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.2007. Min Act: -0.0000

Data Index: 890515 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.2060. Min Act: -0.0000

Data Index: 313719 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1913. Min Act: -0.0000

Data Index: 722858 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1136619 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1328160 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1053202 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1742. Min Act: -0.0000

Data Index: 364374 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1776. Min Act: -0.0000

Data Index: 753368 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1540. Min Act: -0.0000

Data Index: 791701 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.3563. Min Range: -0.3563

Max Act: 0.1775. Min Act: -0.0000

Data Index: 321469 (C4 (Web Text))

Max Activating Token Index: 431