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

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

Neuron 15 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0000

Data Index: 239387 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0935. Min Act: -0.0000

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1277604 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0922. Min Act: -0.0000

Data Index: 751630 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1237012 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1313375 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0898. Min Act: -0.0000

Data Index: 302997 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0862. Min Act: -0.0000

Data Index: 295004 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1414065 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1403832 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1547321 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0792. Min Act: -0.0000

Data Index: 111337 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0860. Min Act: -0.0000

Data Index: 94751 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0672. Min Act: -0.0000

Data Index: 150682 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1492476 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1375991 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0747. Min Act: -0.0000

Data Index: 616274 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0762. Min Act: -0.0000

Data Index: 364178 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1406300 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1094980 (C4 (Web Text))

Max Activating Token Index: 641