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

Dataset: The Pile

Neuron 2820 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1056361 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1939297 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1620611 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0314. Min Act: -0.0000

Data Index: 559734 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1533913 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1395280 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8753. Min Act: -0.0000

Data Index: 258254 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1998032 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9394. Min Act: -0.0000

Data Index: 422497 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1060851 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1355794 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8487. Min Act: -0.0000

Data Index: 475679 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8731. Min Act: -0.0000

Data Index: 272782 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8697. Min Act: -0.0000

Data Index: 688026 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1117252 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1948676 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1971959 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.8108. Min Act: -0.0000

Data Index: 636553 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1837795 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.7778. Min Act: -0.0000

Data Index: 601648 (The Pile)

Max Activating Token Index: 588