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

Dataset: The Pile

Neuron 3748 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.2006. Min Act: -0.0000

Data Index: 860214 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1528027 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1873. Min Act: -0.0000

Data Index: 546421 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1647068 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1908697 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1225839 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1627. Min Act: -0.0000

Data Index: 696689 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1295922 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1638. Min Act: -0.0000

Data Index: 686599 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1674. Min Act: -0.0000

Data Index: 988536 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1901396 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1650. Min Act: -0.0000

Data Index: 207181 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1640. Min Act: -0.0000

Data Index: 400299 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1895531 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1557. Min Act: -0.0000

Data Index: 203291 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1488. Min Act: -0.0000

Data Index: 347316 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1523. Min Act: -0.0000

Data Index: 803699 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1476. Min Act: -0.0000

Data Index: 388931 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1166042 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1409318 (The Pile)

Max Activating Token Index: 94