Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 559 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1323692 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0741. Min Act: -0.0002

Data Index: 367553 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1310468 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0743. Min Act: -0.0001

Data Index: 727614 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0742. Min Act: -0.0002

Data Index: 516902 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0732. Min Act: -0.0002

Data Index: 459792 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0696. Min Act: -0.0002

Data Index: 281070 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0708. Min Act: -0.0002

Data Index: 202787 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1235221 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0716. Min Act: -0.0002

Data Index: 871200 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1107485 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0682. Min Act: -0.0002

Data Index: 111646 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1181204 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0666. Min Act: -0.0002

Data Index: 755133 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1086571 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1306463 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0674. Min Act: -0.0002

Data Index: 938163 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0683. Min Act: -0.0002

Data Index: 977478 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0655. Min Act: -0.0002

Data Index: 253773 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0849. Min Range: -0.0849

Max Act: 0.0659. Min Act: -0.0002

Data Index: 59835 (C4 (Web Text))

Max Activating Token Index: 376