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

Dataset: The Pile

Neuron 246 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: 1.0192. Min Range: -1.0192

Max Act: 1.0192. Min Act: -0.0000

Data Index: 939666 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1580639 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6498. Min Act: -0.0000

Data Index: 587522 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1815927 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1953704 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1365913 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1075535 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.7026. Min Act: -0.0000

Data Index: 500907 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1022309 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6106. Min Act: -0.0000

Data Index: 652659 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6356. Min Act: -0.0000

Data Index: 821783 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1740197 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1478146 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6730. Min Act: -0.0000

Data Index: 999019 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1939928 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6772. Min Act: -0.0000

Data Index: 170740 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6471. Min Act: -0.0000

Data Index: 101333 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6432. Min Act: -0.0000

Data Index: 699477 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1596191 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1409009 (The Pile)

Max Activating Token Index: 977