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

Dataset: The Pile

Neuron 3765 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1216556 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8294. Min Act: -0.0000

Data Index: 679256 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1432927 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7326. Min Act: -0.0000

Data Index: 164056 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1362346 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7103. Min Act: -0.0000

Data Index: 850424 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7023. Min Act: -0.0000

Data Index: 812090 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6513. Min Act: -0.0000

Data Index: 698880 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1801077 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1535956 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1990420 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1897385 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1099861 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1797624 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1065872 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1994468 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6033. Min Act: -0.0000

Data Index: 829473 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6184. Min Act: -0.0000

Data Index: 337981 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1210439 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.6005. Min Act: -0.0000

Data Index: 205517 (The Pile)

Max Activating Token Index: 147