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

Dataset: The Pile

Neuron 5015 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.8381. Min Act: -0.0000

Data Index: 1392600 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5302. Min Act: -0.0000

Data Index: 939458 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.6950. Min Act: -0.0000

Data Index: 1446948 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4898. Min Act: -0.0000

Data Index: 1660555 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4905. Min Act: -0.0000

Data Index: 1939560 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5141. Min Act: -0.0000

Data Index: 1093935 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1353079 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1250716 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3843. Min Act: -0.0000

Data Index: 401373 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3551. Min Act: -0.0000

Data Index: 52500 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3620. Min Act: -0.0000

Data Index: 862748 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1966112 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1696865 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3873. Min Act: -0.0000

Data Index: 175364 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1638732 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2781. Min Act: -0.0000

Data Index: 263629 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1542574 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.1844. Min Act: -0.0000

Data Index: 875278 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1435022 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1481425 (The Pile)

Max Activating Token Index: 723