Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2275 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1850. Min Act: -0.0000

Data Index: 364928 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1187415 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1210322 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1104203 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1814. Min Act: -0.0000

Data Index: 380399 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1264199 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1561. Min Act: -0.0001

Data Index: 568350 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1584. Min Act: -0.0000

Data Index: 831010 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1631. Min Act: -0.0001

Data Index: 347427 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1616. Min Act: -0.0000

Data Index: 942384 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1514. Min Act: -0.0001

Data Index: 454950 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1140348 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1546. Min Act: -0.0000

Data Index: 209507 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1441. Min Act: -0.0000

Data Index: 5657 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1471. Min Act: -0.0000

Data Index: 369733 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1463. Min Act: -0.0000

Data Index: 160430 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1403. Min Act: -0.0001

Data Index: 480591 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1177536 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1463. Min Act: -0.0000

Data Index: 971400 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1363. Min Act: -0.0000

Data Index: 998921 (C4 (Web Text))

Max Activating Token Index: 904