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

Dataset: The Pile

Neuron 4147 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: 1.4008. Min Range: -1.4008

Max Act: 1.4008. Min Act: -0.0000

Data Index: 697145 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.3534. Min Act: -0.0000

Data Index: 565979 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1467482 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1597745 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1624. Min Act: -0.0000

Data Index: 97901 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1512337 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2154. Min Act: -0.0000

Data Index: 351167 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2944. Min Act: -0.0000

Data Index: 758165 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1531099 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.9898. Min Act: -0.0000

Data Index: 969814 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1828792 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1664003 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1832951 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1114047 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1666. Min Act: -0.0000

Data Index: 698042 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1392487 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.0178. Min Act: -0.0000

Data Index: 865040 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.0096. Min Act: -0.0000

Data Index: 309057 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1425. Min Act: -0.0000

Data Index: 295323 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1673155 (The Pile)

Max Activating Token Index: 245