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

Dataset: The Pile

Neuron 3751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0699. Min Range: -1.0699

Max Act: 1.0699. Min Act: -0.0000

Data Index: 365441 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.9799. Min Act: -0.0000

Data Index: 871780 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1600325 (The Pile)

Max Activating Token Index: 95

Text #3

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.8330. Min Act: -0.0000

Data Index: 486116 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1018394 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1533014 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1988345 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7653. Min Act: -0.0000

Data Index: 49192 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1134645 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7165. Min Act: -0.0000

Data Index: 191931 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1268104 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7062. Min Act: -0.0000

Data Index: 182615 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1340906 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1647247 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1686905 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6548. Min Act: -0.0000

Data Index: 783627 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6381. Min Act: -0.0000

Data Index: 747108 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6482. Min Act: -0.0000

Data Index: 254416 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1810130 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1625924 (The Pile)

Max Activating Token Index: 789