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

Dataset: The Pile

Neuron 1313 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: 3.7888. Min Range: -3.7888

Max Act: 3.6201. Min Act: -0.0000

Data Index: 1926023 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.6058. Min Act: -0.0000

Data Index: 1763675 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.5144. Min Act: -0.0000

Data Index: 527617 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.3693. Min Act: -0.0000

Data Index: 20321 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1882. Min Act: -0.0000

Data Index: 1096813 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.7888. Min Act: -0.0000

Data Index: 717537 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.5130. Min Act: -0.0000

Data Index: 773552 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1631. Min Act: -0.0000

Data Index: 1308427 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.3880. Min Act: -0.0000

Data Index: 62999 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1534. Min Act: -0.0000

Data Index: 1926419 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 3.7888. Min Range: -3.7888

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1559201 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1056. Min Act: -0.0000

Data Index: 1136989 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1901. Min Act: -0.0000

Data Index: 900659 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1311. Min Act: -0.0000

Data Index: 1563785 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 3.7888. Min Range: -3.7888

Max Act: 2.5884. Min Act: -0.0000

Data Index: 283188 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 3.7888. Min Range: -3.7888

Max Act: 2.7965. Min Act: -0.0000

Data Index: 715545 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 3.7888. Min Range: -3.7888

Max Act: 3.1178. Min Act: -0.0000

Data Index: 1755605 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 3.7888. Min Range: -3.7888

Max Act: 2.9620. Min Act: -0.0000

Data Index: 1844448 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 3.7888. Min Range: -3.7888

Max Act: 2.8602. Min Act: -0.0000

Data Index: 296797 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 3.7888. Min Range: -3.7888

Max Act: 2.5903. Min Act: -0.0000

Data Index: 1753164 (The Pile)

Max Activating Token Index: 754