Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 213 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1104725 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1171784 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0765. Min Act: -0.0003

Data Index: 211305 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0772. Min Act: -0.0002

Data Index: 25715 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0769. Min Act: -0.0003

Data Index: 670859 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0758. Min Act: -0.0003

Data Index: 345569 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0766. Min Act: -0.0003

Data Index: 115543 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0754. Min Act: -0.0003

Data Index: 554374 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0742. Min Act: -0.0003

Data Index: 1113979 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0718. Min Act: -0.0003

Data Index: 173556 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0750. Min Act: -0.0002

Data Index: 770987 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0759. Min Act: -0.0003

Data Index: 830554 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0747. Min Act: -0.0003

Data Index: 247079 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0727. Min Act: -0.0003

Data Index: 817220 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0695. Min Act: -0.0003

Data Index: 262036 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0706. Min Act: -0.0002

Data Index: 89569 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0707. Min Act: -0.0003

Data Index: 381871 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0709. Min Act: -0.0004

Data Index: 114452 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0717. Min Act: -0.0002

Data Index: 803521 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1075094 (C4 (Web Text))

Max Activating Token Index: 929