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

Dataset: The Pile

Neuron 4270 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1459646 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.2012. Min Act: -0.0000

Data Index: 793930 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1980. Min Act: -0.0000

Data Index: 614972 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1070381 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1959. Min Act: -0.0000

Data Index: 871727 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1539240 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1807. Min Act: -0.0000

Data Index: 99850 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1120137 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1784. Min Act: -0.0000

Data Index: 55350 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1780. Min Act: -0.0000

Data Index: 602494 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1727. Min Act: -0.0000

Data Index: 525566 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1889221 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1228200 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1635. Min Act: -0.0000

Data Index: 472806 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1658147 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1592529 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1443942 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1424. Min Act: -0.0000

Data Index: 112572 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1881677 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1448064 (The Pile)

Max Activating Token Index: 1023