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

Dataset: The Pile

Neuron 4928 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: 1.8695. Min Range: -1.8695

Max Act: 1.8282. Min Act: -0.0000

Data Index: 1866790 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.7495. Min Act: -0.0000

Data Index: 976196 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.7999. Min Act: -0.0000

Data Index: 1121735 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.8695. Min Act: -0.0000

Data Index: 775116 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.8432. Min Act: -0.0000

Data Index: 628536 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6721. Min Act: -0.0000

Data Index: 340442 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.2552. Min Act: -0.0000

Data Index: 54031 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1057466 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6343. Min Act: -0.0000

Data Index: 1166468 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1595774 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.4993. Min Act: -0.0000

Data Index: 731530 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5952. Min Act: -0.0000

Data Index: 113206 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.4402. Min Act: -0.0000

Data Index: 204744 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5094. Min Act: -0.0000

Data Index: 572408 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5219. Min Act: -0.0000

Data Index: 258469 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5808. Min Act: -0.0000

Data Index: 162727 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1780409 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5698. Min Act: -0.0000

Data Index: 1700064 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1441892 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5545. Min Act: -0.0000

Data Index: 872058 (The Pile)

Max Activating Token Index: 347