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

Dataset: The Pile

Neuron 547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1903. Min Range: -3.1903

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1545454 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.5631. Min Act: -0.0000

Data Index: 695630 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.6900. Min Act: -0.0000

Data Index: 646262 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.2909. Min Act: -0.0000

Data Index: 1305712 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.5325. Min Act: -0.0000

Data Index: 1496412 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3628. Min Act: -0.0000

Data Index: 831107 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.2654. Min Act: -0.0000

Data Index: 42146 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.5110. Min Act: -0.0000

Data Index: 1712290 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1522601 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.4006. Min Act: -0.0000

Data Index: 1201322 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3760. Min Act: -0.0000

Data Index: 207970 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3820. Min Act: -0.0000

Data Index: 950903 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1955713 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1928236 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3637. Min Act: -0.0000

Data Index: 754622 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.2195. Min Act: -0.0000

Data Index: 1603813 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1071000 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.1435. Min Act: -0.0000

Data Index: 291373 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.1703. Min Act: -0.0000

Data Index: 855481 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.8480. Min Act: -0.0000

Data Index: 848626 (The Pile)

Max Activating Token Index: 951