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

Dataset: The Pile

Neuron 2941 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: 0.6960. Min Range: -0.6960

Max Act: 0.6960. Min Act: 0.0000

Data Index: 1922998 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6829. Min Act: -0.0000

Data Index: 711809 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6297. Min Act: 0.0000

Data Index: 995997 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1061509 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1280331 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1775412 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1804454 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5100. Min Act: -0.0000

Data Index: 259649 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1806003 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5011. Min Act: 0.0000

Data Index: 1580961 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1566054 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4889. Min Act: 0.0000

Data Index: 121963 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1749970 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1803285 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4774. Min Act: -0.0000

Data Index: 357494 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1738787 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4262. Min Act: -0.0000

Data Index: 14052 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4499. Min Act: 0.0000

Data Index: 1907218 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1808632 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1990880 (The Pile)

Max Activating Token Index: 162