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

Dataset: The Pile

Neuron 646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2600. Min Act: -0.0000

Data Index: 731989 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1824061 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1051097 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1876. Min Act: -0.0000

Data Index: 573577 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1500236 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1090138 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1311226 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1867. Min Act: -0.0000

Data Index: 996046 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1806. Min Act: -0.0000

Data Index: 920799 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1226680 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1771. Min Act: -0.0000

Data Index: 129084 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1721. Min Act: -0.0000

Data Index: 194885 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1734. Min Act: -0.0000

Data Index: 905197 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1954358 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1310596 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1736. Min Act: -0.0000

Data Index: 722617 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1619. Min Act: -0.0000

Data Index: 755452 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1633. Min Act: -0.0000

Data Index: 223885 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1147125 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1399382 (The Pile)

Max Activating Token Index: 1019