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

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

Neuron 2650 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1613472 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1472734 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1553454 (Python Code)

Max Activating Token Index: 324

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1524222 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1481006 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1386256 (Python Code)

Max Activating Token Index: 519

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1546984 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1578575 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1594059 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1560374 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1541371 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1461342 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1528570 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1451596 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1616056 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1475818 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1370328 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1429539 (Python Code)

Max Activating Token Index: 660

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1410943 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1413060 (Python Code)

Max Activating Token Index: 162