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

Dataset: The Pile

Neuron 1905 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: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1879683 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1984. Min Act: -0.0000

Data Index: 164607 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1865. Min Act: -0.0000

Data Index: 687528 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1894. Min Act: -0.0000

Data Index: 809052 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1621061 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1952879 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1068445 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1814644 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1738. Min Act: -0.0000

Data Index: 204105 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1189210 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1650. Min Act: -0.0000

Data Index: 646243 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1673. Min Act: -0.0000

Data Index: 488148 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1350994 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1373206 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1674. Min Act: -0.0000

Data Index: 150380 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1658. Min Act: -0.0000

Data Index: 282888 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1737785 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1213836 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1525. Min Act: -0.0000

Data Index: 715752 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1647. Min Act: -0.0000

Data Index: 832935 (The Pile)

Max Activating Token Index: 853