Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1497 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9836. Min Act: -0.0000

Data Index: 645485 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1768750 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9208. Min Act: -0.0000

Data Index: 490318 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9255. Min Act: -0.0000

Data Index: 170123 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1479723 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1340076 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.7943. Min Act: -0.0000

Data Index: 733305 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1415567 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.7230. Min Act: -0.0000

Data Index: 226825 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.7166. Min Act: 0.0000

Data Index: 1708403 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6291. Min Act: -0.0000

Data Index: 535547 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1218524 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6196. Min Act: -0.0000

Data Index: 969845 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6784. Min Act: -0.0000

Data Index: 384664 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6247. Min Act: -0.0000

Data Index: 788147 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6148. Min Act: -0.0000

Data Index: 433814 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1066621 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6336. Min Act: 0.0000

Data Index: 1583774 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1770623 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.6839. Min Act: -0.0000

Data Index: 205465 (The Pile)

Max Activating Token Index: 380