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

Dataset: The Pile

Neuron 4601 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: 0.2493. Min Range: -0.2493

Max Act: 0.2493. Min Act: -0.0000

Data Index: 704537 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1368365 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1539841 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2009. Min Act: -0.0000

Data Index: 491141 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1298119 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1535311 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1718553 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2077. Min Act: -0.0000

Data Index: 800614 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2010. Min Act: -0.0000

Data Index: 178086 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1946. Min Act: -0.0000

Data Index: 898368 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1783553 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1499505 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1131100 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1463393 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1821. Min Act: -0.0000

Data Index: 161391 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1070336 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1226396 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1520818 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1491. Min Act: -0.0000

Data Index: 763000 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1831. Min Act: -0.0000

Data Index: 202734 (The Pile)

Max Activating Token Index: 580