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

Dataset: The Pile

Neuron 4011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.6617. Min Act: -0.0000

Data Index: 734050 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5973. Min Act: -0.0000

Data Index: 825524 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1885586 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5804. Min Act: -0.0000

Data Index: 175450 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5777. Min Act: -0.0000

Data Index: 795050 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1711959 (The Pile)

Max Activating Token Index: 790

Text #6

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1595202 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5648. Min Act: -0.0000

Data Index: 590576 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1221897 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1861029 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1854908 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5575. Min Act: -0.0000

Data Index: 863636 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5585. Min Act: -0.0000

Data Index: 791676 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5423. Min Act: -0.0000

Data Index: 271055 (The Pile)

Max Activating Token Index: 135

Text #14

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1338315 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5645. Min Act: -0.0000

Data Index: 405738 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5475. Min Act: -0.0000

Data Index: 397000 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1954359 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1914829 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1257614 (The Pile)

Max Activating Token Index: 544