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

Dataset: The Pile

Neuron 1659 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1355958 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1221061 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4054. Min Act: -0.0000

Data Index: 586963 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1406583 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4412. Min Act: -0.0000

Data Index: 840657 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1382561 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1713996 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2946. Min Act: -0.0000

Data Index: 857236 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1976964 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2794. Min Act: -0.0000

Data Index: 961637 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2320. Min Act: -0.0000

Data Index: 832517 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2642. Min Act: -0.0000

Data Index: 227567 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1305289 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1239932 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1404430 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1178994 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2108. Min Act: -0.0000

Data Index: 92489 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1039652 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1694066 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1983179 (The Pile)

Max Activating Token Index: 532