Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2985 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1374725 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 480219 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1993850 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1576. Min Act: -0.0000

Data Index: 306720 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1022235 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1001369 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1533. Min Act: -0.0000

Data Index: 233073 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1908650 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1777. Min Act: -0.0000

Data Index: 366151 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1590. Min Act: -0.0000

Data Index: 379394 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1273954 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1511. Min Act: -0.0000

Data Index: 925302 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1906848 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1644. Min Act: -0.0000

Data Index: 58186 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1364669 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1707. Min Act: -0.0001

Data Index: 820791 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1462. Min Act: -0.0000

Data Index: 93188 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1621. Min Act: -0.0000

Data Index: 374361 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1672. Min Act: -0.0000

Data Index: 706115 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1937204 (The Pile)

Max Activating Token Index: 349