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

Dataset: The Pile

Neuron 4322 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1597872 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1751588 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1748. Min Act: -0.0000

Data Index: 146742 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1582. Min Act: -0.0000

Data Index: 626557 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1625. Min Act: -0.0000

Data Index: 683738 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1554. Min Act: -0.0000

Data Index: 465950 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1509. Min Act: -0.0000

Data Index: 312099 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1511. Min Act: -0.0000

Data Index: 916772 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1603046 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1567. Min Act: -0.0000

Data Index: 894365 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1063069 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1166851 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1872528 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1564. Min Act: -0.0000

Data Index: 454317 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1325. Min Act: -0.0000

Data Index: 741196 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1374. Min Act: -0.0000

Data Index: 753587 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1007699 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1284. Min Act: -0.0000

Data Index: 614399 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1376108 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1340. Min Act: -0.0000

Data Index: 477320 (The Pile)

Max Activating Token Index: 862