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

Dataset: The Pile

Neuron 704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1113281 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1478026 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1641. Min Act: -0.0000

Data Index: 351368 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1834. Min Act: -0.0000

Data Index: 288549 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1755. Min Act: -0.0000

Data Index: 133649 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1735. Min Act: -0.0000

Data Index: 754209 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1605046 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1613. Min Act: -0.0000

Data Index: 937642 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1568. Min Act: -0.0000

Data Index: 600039 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1558. Min Act: -0.0000

Data Index: 380436 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1621409 (The Pile)

Max Activating Token Index: 390

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1253273 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1340655 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1022544 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1480. Min Act: -0.0000

Data Index: 102804 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1415966 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1591446 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1518. Min Act: -0.0000

Data Index: 893590 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1909140 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1534. Min Act: -0.0000

Data Index: 397477 (The Pile)

Max Activating Token Index: 639