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

Dataset: The Pile

Neuron 4932 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: 1.7393. Min Range: -1.7393

Max Act: 1.7393. Min Act: -0.0000

Data Index: 601650 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3206. Min Act: -0.0000

Data Index: 812295 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1312055 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1154244 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.2134. Min Act: -0.0000

Data Index: 845626 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1023479 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.2182. Min Act: -0.0000

Data Index: 33239 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1280815 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1933184 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1738379 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1483537 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0624. Min Act: -0.0000

Data Index: 800807 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1558857 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0103. Min Act: -0.0000

Data Index: 998078 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 1.7393. Min Range: -1.7393

Max Act: 0.9976. Min Act: -0.0000

Data Index: 91484 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 1.7393. Min Range: -1.7393

Max Act: 0.9990. Min Act: -0.0000

Data Index: 721720 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 1.7393. Min Range: -1.7393

Max Act: 0.9566. Min Act: -0.0000

Data Index: 525747 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 1.7393. Min Range: -1.7393

Max Act: 0.9361. Min Act: -0.0000

Data Index: 33616 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.7393. Min Range: -1.7393

Max Act: 0.9146. Min Act: -0.0000

Data Index: 485766 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.0523. Min Act: -0.0000

Data Index: 973003 (The Pile)

Max Activating Token Index: 1004