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

Dataset: The Pile

Neuron 3046 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1065758 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1012917 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1568906 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1178286 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1322138 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9578. Min Act: -0.0000

Data Index: 937611 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0023. Min Act: -0.0000

Data Index: 361723 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1163645 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1121894 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9430. Min Act: -0.0000

Data Index: 697289 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9514. Min Act: -0.0000

Data Index: 471850 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0026. Min Act: -0.0000

Data Index: 18827 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1741310 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1864169 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1076939 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.7959. Min Act: -0.0000

Data Index: 688298 (The Pile)

Max Activating Token Index: 930

Text #16

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1637772 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1996318 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9262. Min Act: -0.0000

Data Index: 493295 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1878262 (The Pile)

Max Activating Token Index: 609