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

Dataset: The Pile

Neuron 863 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: 5.0094. Min Range: -5.0094

Max Act: 3.9066. Min Act: -0.0000

Data Index: 1954263 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 5.0094. Min Range: -5.0094

Max Act: 5.0094. Min Act: -0.0000

Data Index: 1422228 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.3895. Min Act: -0.0000

Data Index: 865960 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.1140. Min Act: -0.0000

Data Index: 193127 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.3921. Min Act: -0.0000

Data Index: 1754627 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.8415. Min Act: -0.0000

Data Index: 34170 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 5.0094. Min Range: -5.0094

Max Act: 2.4762. Min Act: -0.0000

Data Index: 894078 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.4466. Min Act: -0.0000

Data Index: 1013532 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.3498. Min Act: -0.0000

Data Index: 661949 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.3101. Min Act: -0.0000

Data Index: 471693 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 5.0094. Min Range: -5.0094

Max Act: 2.7523. Min Act: -0.0000

Data Index: 1070727 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.4424. Min Act: -0.0000

Data Index: 918792 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.1760. Min Act: -0.0000

Data Index: 480687 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 5.0094. Min Range: -5.0094

Max Act: 2.7030. Min Act: -0.0000

Data Index: 1162427 (The Pile)

Max Activating Token Index: 1001

Text #14

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.3856. Min Act: -0.0000

Data Index: 420956 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.3790. Min Act: -0.0000

Data Index: 1296369 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 5.0094. Min Range: -5.0094

Max Act: 3.0826. Min Act: -0.0000

Data Index: 403260 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 5.0094. Min Range: -5.0094

Max Act: 2.8250. Min Act: -0.0000

Data Index: 888803 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 5.0094. Min Range: -5.0094

Max Act: 2.4611. Min Act: -0.0000

Data Index: 1405573 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 5.0094. Min Range: -5.0094

Max Act: 2.2949. Min Act: -0.0000

Data Index: 650706 (The Pile)

Max Activating Token Index: 353