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

Dataset: The Pile

Neuron 4494 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: 1.1787. Min Range: -1.1787

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1285695 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.0839. Min Act: -0.0000

Data Index: 402112 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1439107 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9346. Min Act: -0.0000

Data Index: 785032 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9008. Min Act: -0.0000

Data Index: 76131 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1907813 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8424. Min Act: -0.0000

Data Index: 365077 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8808. Min Act: -0.0000

Data Index: 57102 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9223. Min Act: -0.0000

Data Index: 283865 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8685. Min Act: -0.0000

Data Index: 191549 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1970507 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8207. Min Act: -0.0000

Data Index: 942968 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1474694 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1015901 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8601. Min Act: -0.0000

Data Index: 453753 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7527. Min Act: -0.0000

Data Index: 415210 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8033. Min Act: -0.0000

Data Index: 800606 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7983. Min Act: -0.0000

Data Index: 780006 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8350. Min Act: -0.0000

Data Index: 231592 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7773. Min Act: -0.0000

Data Index: 570380 (The Pile)

Max Activating Token Index: 463