Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1110 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1544993 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1411890 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1467482 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1609641 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1630039 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1652938 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1372706 (Python Code)

Max Activating Token Index: 147

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1572374 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0722. Min Act: -0.0001

Data Index: 426391 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0739. Min Act: -0.0001

Data Index: 493061 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1525862 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1101708 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0659. Min Act: -0.0000

Data Index: 214694 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1481244 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1596558 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1522189 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0739. Min Act: -0.0000

Data Index: 730318 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1601944 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1288344 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1550244 (Python Code)

Max Activating Token Index: 283