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

Dataset: The Pile

Neuron 4425 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5928. Min Act: -0.0000

Data Index: 858860 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4582. Min Act: -0.0000

Data Index: 1845618 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.3278. Min Act: -0.0000

Data Index: 1904426 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.1507. Min Act: -0.0000

Data Index: 1701720 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.2491. Min Act: -0.0000

Data Index: 577165 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.1088. Min Act: -0.0000

Data Index: 1875483 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.1240. Min Act: -0.0000

Data Index: 667868 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.0197. Min Act: -0.0000

Data Index: 1889610 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.1082. Min Act: -0.0000

Data Index: 1395122 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.0797. Min Act: -0.0000

Data Index: 1967947 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.1002. Min Act: -0.0000

Data Index: 545379 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 3.5928. Min Range: -3.5928

Max Act: 2.9354. Min Act: -0.0000

Data Index: 1688324 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.2016. Min Act: -0.0000

Data Index: 160671 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1675858 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 3.5928. Min Range: -3.5928

Max Act: 2.8784. Min Act: -0.0000

Data Index: 345111 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.0400. Min Act: -0.0000

Data Index: 1688339 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.1423. Min Act: -0.0000

Data Index: 666527 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 3.5928. Min Range: -3.5928

Max Act: 2.9928. Min Act: -0.0000

Data Index: 27566 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 3.5928. Min Range: -3.5928

Max Act: 2.9717. Min Act: -0.0000

Data Index: 1121409 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 3.5928. Min Range: -3.5928

Max Act: 2.9558. Min Act: -0.0000

Data Index: 1628054 (The Pile)

Max Activating Token Index: 275