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

Dataset: The Pile

Neuron 5013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1014. Min Act: -0.0000

Data Index: 1761816 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1099555 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1015181 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0272. Min Act: -0.0000

Data Index: 503286 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9435. Min Act: -0.0000

Data Index: 871607 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8434. Min Act: -0.0000

Data Index: 832893 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1061969 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1947839 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8615. Min Act: -0.0000

Data Index: 887998 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1846532 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8773. Min Act: -0.0000

Data Index: 573232 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8156. Min Act: -0.0000

Data Index: 698812 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7802. Min Act: -0.0000

Data Index: 193471 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1165597 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1551942 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1403916 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1966324 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1081836 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1843130 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7250. Min Act: -0.0000

Data Index: 332828 (The Pile)

Max Activating Token Index: 991