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

Dataset: The Pile

Neuron 1376 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2559. Min Act: -0.0000

Data Index: 322996 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1993. Min Act: 0.0000

Data Index: 1526410 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1209351 (The Pile)

Max Activating Token Index: 932

Text #3

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1826. Min Act: -0.0000

Data Index: 410536 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1920. Min Act: -0.0000

Data Index: 591203 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1608016 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1630226 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1971. Min Act: -0.0000

Data Index: 895879 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2069. Min Act: -0.0000

Data Index: 470048 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1335120 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1666. Min Act: 0.0000

Data Index: 107367 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1693272 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1818. Min Act: -0.0000

Data Index: 865379 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1852. Min Act: -0.0000

Data Index: 863952 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1773. Min Act: -0.0000

Data Index: 627890 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1430896 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1132615 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1537690 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1371312 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1299919 (The Pile)

Max Activating Token Index: 717