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

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

Neuron 3988 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: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0001

Data Index: 521384 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0948. Min Act: -0.0000

Data Index: 174411 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0063. Min Act: -0.0000

Data Index: 676179 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1269350 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8791. Min Act: -0.0000

Data Index: 912489 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8754. Min Act: -0.0000

Data Index: 559597 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8421. Min Act: -0.0000

Data Index: 744937 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8675. Min Act: -0.0001

Data Index: 627255 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1313408 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8083. Min Act: -0.0000

Data Index: 259063 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7920. Min Act: -0.0000

Data Index: 211264 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7603. Min Act: -0.0000

Data Index: 646443 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1099254 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7869. Min Act: -0.0000

Data Index: 105658 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1055403 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7250. Min Act: -0.0000

Data Index: 379954 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7493. Min Act: -0.0001

Data Index: 145302 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7414. Min Act: -0.0000

Data Index: 425685 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7428. Min Act: -0.0000

Data Index: 507122 (C4 (Web Text))

Max Activating Token Index: 18