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

Dataset: The Pile

Neuron 3773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1818653 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2372. Min Act: -0.0000

Data Index: 202964 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2091. Min Act: -0.0000

Data Index: 109795 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1147865 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1704270 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1121619 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1766. Min Act: -0.0000

Data Index: 669948 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1660. Min Act: -0.0000

Data Index: 479856 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1529. Min Act: -0.0000

Data Index: 801528 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1156799 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1673. Min Act: -0.0000

Data Index: 991527 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1734. Min Act: -0.0000

Data Index: 390562 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1513863 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1469. Min Act: -0.0000

Data Index: 372712 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1332302 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1558696 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1591302 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1889213 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1541. Min Act: -0.0000

Data Index: 957744 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1434. Min Act: -0.0000

Data Index: 981568 (The Pile)

Max Activating Token Index: 1011