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

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

Neuron 1598 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1185616 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0003

Data Index: 506809 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1638859 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1568253 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1644337 (Python Code)

Max Activating Token Index: 165

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1487969 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0646. Min Act: -0.0003

Data Index: 459990 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1516075 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1133222 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0631. Min Act: -0.0002

Data Index: 374922 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1563010 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0604. Min Act: -0.0002

Data Index: 709163 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1170150 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1589286 (Python Code)

Max Activating Token Index: 183

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1448493 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0583. Min Act: -0.0003

Data Index: 337440 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1632142 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1497391 (Python Code)

Max Activating Token Index: 99

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1636355 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1526713 (Python Code)

Max Activating Token Index: 35