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

Dataset: The Pile

Neuron 2680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.1889. Min Act: -0.0000

Data Index: 354799 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.2193. Min Act: -0.0000

Data Index: 315696 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.2479. Min Act: -0.0000

Data Index: 835706 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0943. Min Act: -0.0000

Data Index: 547361 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1676994 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0650. Min Act: -0.0000

Data Index: 470907 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0499. Min Act: -0.0000

Data Index: 511871 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1492476 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0781. Min Act: -0.0000

Data Index: 686084 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.1069. Min Act: -0.0000

Data Index: 339549 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0620. Min Act: -0.0000

Data Index: 988572 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.2479. Min Range: -1.2479

Max Act: 0.9960. Min Act: -0.0000

Data Index: 239690 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1237368 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1877778 (The Pile)

Max Activating Token Index: 19

Text #14

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0368. Min Act: -0.0000

Data Index: 159418 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.2479. Min Range: -1.2479

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1067098 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1622124 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0573. Min Act: -0.0000

Data Index: 270626 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1591739 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 1.2479. Min Range: -1.2479

Max Act: 1.0216. Min Act: -0.0000

Data Index: 680831 (The Pile)

Max Activating Token Index: 125