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

Dataset: The Pile

Neuron 1638 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1066770 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1020844 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1637453 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1816. Min Act: -0.0000

Data Index: 660078 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1231303 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1111. Min Act: -0.0000

Data Index: 408227 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1037. Min Act: -0.0000

Data Index: 351610 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1563104 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0599. Min Act: -0.0000

Data Index: 913530 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0842. Min Act: -0.0000

Data Index: 274628 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1026. Min Act: -0.0000

Data Index: 570114 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0310. Min Act: -0.0000

Data Index: 624912 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0903. Min Act: -0.0000

Data Index: 259757 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0826. Min Act: -0.0000

Data Index: 976493 (The Pile)

Max Activating Token Index: 889

Text #14

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1914521 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9814. Min Act: -0.0000

Data Index: 272575 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1780221 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1157857 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1958743 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1488347 (The Pile)

Max Activating Token Index: 802