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

Dataset: The Pile

Neuron 3012 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: 1.1959. Min Range: -1.1959

Max Act: 1.0097. Min Act: -0.0000

Data Index: 379613 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1959. Min Act: -0.0000

Data Index: 451155 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0809. Min Act: -0.0000

Data Index: 813463 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0108. Min Act: -0.0000

Data Index: 615448 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0078. Min Act: -0.0000

Data Index: 965686 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9632. Min Act: -0.0000

Data Index: 539161 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1882503 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1072978 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1695733 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1539051 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9684. Min Act: -0.0000

Data Index: 439944 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9646. Min Act: -0.0000

Data Index: 838462 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9609. Min Act: -0.0000

Data Index: 216050 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1572360 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1903867 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9014. Min Act: -0.0000

Data Index: 482094 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1139080 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1196852 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1521294 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1515926 (The Pile)

Max Activating Token Index: 526