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

Dataset: The Pile

Neuron 4245 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.3170. Min Act: 0.0000

Data Index: 1604484 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1910605 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1404779 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1940728 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1637. Min Act: -0.0000

Data Index: 481661 (The Pile)

Max Activating Token Index: 291

Text #5

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1745900 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1858378 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1311861 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1390. Min Act: -0.0000

Data Index: 393826 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1391. Min Act: -0.0000

Data Index: 170919 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1641. Min Act: -0.0000

Data Index: 507967 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1423. Min Act: 0.0000

Data Index: 1681106 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1471. Min Act: 0.0000

Data Index: 1177871 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1551. Min Act: 0.0000

Data Index: 124304 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1405. Min Act: -0.0000

Data Index: 236788 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1455. Min Act: -0.0000

Data Index: 364098 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1484. Min Act: -0.0000

Data Index: 610873 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1541983 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1493535 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1428. Min Act: -0.0000

Data Index: 597031 (The Pile)

Max Activating Token Index: 782