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

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

Neuron 3944 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1570590 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1092113 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0677. Min Act: -0.0002

Data Index: 926286 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0623. Min Act: -0.0002

Data Index: 599645 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0624. Min Act: -0.0002

Data Index: 103100 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1650755 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1627003 (Python Code)

Max Activating Token Index: 816

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0623. Min Act: -0.0002

Data Index: 965400 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0625. Min Act: -0.0002

Data Index: 539368 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0605. Min Act: -0.0002

Data Index: 464315 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1501148 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1591773 (Python Code)

Max Activating Token Index: 332

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1547128 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1075680 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1622100 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0608. Min Act: -0.0002

Data Index: 871888 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0590. Min Act: -0.0002

Data Index: 993887 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0596. Min Act: -0.0002

Data Index: 605415 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0604. Min Act: -0.0002

Data Index: 564727 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0584. Min Act: -0.0002

Data Index: 802171 (C4 (Web Text))

Max Activating Token Index: 611