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

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

Neuron 4254 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: 4.1904. Min Range: -4.1904

Max Act: 4.1904. Min Act: -0.0000

Data Index: 171706 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 4.1904. Min Range: -4.1904

Max Act: 4.0814. Min Act: -0.0000

Data Index: 1304306 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 4.1904. Min Range: -4.1904

Max Act: 4.1094. Min Act: -0.0000

Data Index: 1062733 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.8245. Min Act: -0.0000

Data Index: 340855 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.6250. Min Act: -0.0000

Data Index: 159894 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.3575. Min Act: -0.0000

Data Index: 218253 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.5080. Min Act: -0.0000

Data Index: 318679 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.4558. Min Act: -0.0000

Data Index: 380128 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.1444. Min Act: -0.0000

Data Index: 837266 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.5754. Min Act: -0.0000

Data Index: 607895 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 4.1904. Min Range: -4.1904

Max Act: 2.7700. Min Act: -0.0000

Data Index: 1099081 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.3653. Min Act: -0.0000

Data Index: 585759 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.0770. Min Act: -0.0000

Data Index: 677387 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.3622. Min Act: -0.0000

Data Index: 1229707 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.2608. Min Act: -0.0000

Data Index: 1078018 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 4.1904. Min Range: -4.1904

Max Act: 2.8229. Min Act: -0.0000

Data Index: 335111 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.2214. Min Act: -0.0000

Data Index: 1268957 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.3559. Min Act: -0.0000

Data Index: 955859 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.3365. Min Act: -0.0000

Data Index: 1281711 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 4.1904. Min Range: -4.1904

Max Act: 3.2031. Min Act: -0.0000

Data Index: 874856 (C4 (Web Text))

Max Activating Token Index: 558