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

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

Neuron 2434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0000

Data Index: 621705 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1625028 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1575796 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1363373 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1438641 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1459866 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1456576 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1647419 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1536370 (Python Code)

Max Activating Token Index: 540

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1444566 (Python Code)

Max Activating Token Index: 481

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1606706 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1595104 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0811. Min Act: -0.0000

Data Index: 772528 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1614520 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1524512 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1483570 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1444908 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0729. Min Act: -0.0000

Data Index: 243137 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1655733 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1656430 (Python Code)

Max Activating Token Index: 992