Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3860 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1420. Min Act: -0.0000

Data Index: 202834 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1065. Min Act: -0.0000

Data Index: 597733 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1090046 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1111. Min Act: -0.0000

Data Index: 796750 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1019. Min Act: -0.0000

Data Index: 807105 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0898. Min Act: -0.0000

Data Index: 648781 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0973. Min Act: -0.0000

Data Index: 565596 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0861. Min Act: -0.0000

Data Index: 933765 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1271351 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1241912 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1090512 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0951. Min Act: -0.0000

Data Index: 745596 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0894. Min Act: -0.0000

Data Index: 40273 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1185530 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0866. Min Act: 0.0001

Data Index: 1598666 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0902. Min Act: -0.0000

Data Index: 397166 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0892. Min Act: 0.0000

Data Index: 1570087 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0936. Min Act: -0.0000

Data Index: 378957 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1343060 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0905. Min Act: -0.0000

Data Index: 649220 (C4 (Web Text))

Max Activating Token Index: 39