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

Dataset: The Pile

Neuron 906 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: 0.2095. Min Range: -0.2095

Max Act: 0.2095. Min Act: 0.0000

Data Index: 546273 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1970. Min Act: 0.0000

Data Index: 1345566 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1546030 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1903. Min Act: 0.0000

Data Index: 1878552 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1826. Min Act: 0.0000

Data Index: 1984007 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1757. Min Act: -0.0000

Data Index: 400172 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1228707 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1721. Min Act: -0.0000

Data Index: 933166 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1598. Min Act: 0.0000

Data Index: 821937 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1569. Min Act: 0.0000

Data Index: 551184 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1960892 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1596614 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1474. Min Act: 0.0000

Data Index: 370022 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1459. Min Act: 0.0000

Data Index: 465124 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1095438 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1443. Min Act: 0.0000

Data Index: 878070 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1432. Min Act: 0.0000

Data Index: 1289775 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1413. Min Act: -0.0000

Data Index: 833311 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1412. Min Act: -0.0000

Data Index: 714959 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1406. Min Act: 0.0000

Data Index: 1818021 (The Pile)

Max Activating Token Index: 346