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

Dataset: The Pile

Neuron 1313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 242890 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1568794 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2379. Min Act: -0.0000

Data Index: 787048 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2160. Min Act: -0.0000

Data Index: 754451 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2042. Min Act: -0.0000

Data Index: 396008 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1610999 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1467449 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1872370 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1640070 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1123943 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1664. Min Act: -0.0000

Data Index: 142063 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1950530 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1382450 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1603. Min Act: -0.0000

Data Index: 656569 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1560. Min Act: -0.0000

Data Index: 158217 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1002098 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1413. Min Act: -0.0000

Data Index: 947416 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1680278 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1683130 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1521. Min Act: -0.0000

Data Index: 922981 (The Pile)

Max Activating Token Index: 794