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

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

Neuron 3966 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0001

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0819. Min Act: -0.0001

Data Index: 825929 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0822. Min Act: -0.0001

Data Index: 119633 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1301723 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0864. Min Act: -0.0001

Data Index: 677928 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0801. Min Act: -0.0001

Data Index: 232932 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1313056 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0753. Min Act: -0.0001

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1180138 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1372194 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1420537 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0733. Min Act: -0.0001

Data Index: 516922 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1040615 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1614608 (Python Code)

Max Activating Token Index: 530

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1387311 (Python Code)

Max Activating Token Index: 978

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0722. Min Act: -0.0001

Data Index: 507126 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0731. Min Act: -0.0001

Data Index: 718875 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0667. Min Act: -0.0001

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 424