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

Dataset: The Pile

Neuron 3551 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: 0.2528. Min Range: -0.2528

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1015075 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2116. Min Act: -0.0000

Data Index: 792014 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2528. Min Act: -0.0000

Data Index: 638961 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2131. Min Act: -0.0000

Data Index: 764840 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1528105 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1719. Min Act: -0.0000

Data Index: 964903 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1504. Min Act: -0.0000

Data Index: 460485 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1098662 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2063. Min Act: -0.0000

Data Index: 17649 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1865. Min Act: -0.0000

Data Index: 613628 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1826. Min Act: -0.0000

Data Index: 412847 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1570469 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1510. Min Act: -0.0000

Data Index: 245453 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1093242 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1008527 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1866. Min Act: -0.0000

Data Index: 641758 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1464299 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1485. Min Act: -0.0000

Data Index: 322732 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1700. Min Act: -0.0000

Data Index: 986313 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1523. Min Act: -0.0000

Data Index: 450255 (The Pile)

Max Activating Token Index: 68