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

Dataset: The Pile

Neuron 2780 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.2556. Min Act: -0.0000

Data Index: 1763810 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.8181. Min Act: -0.0000

Data Index: 639294 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.6911. Min Act: -0.0000

Data Index: 542392 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.5950. Min Act: -0.0000

Data Index: 1036791 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.4756. Min Act: -0.0000

Data Index: 1197207 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 5.0433. Min Range: -5.0433

Max Act: 5.0433. Min Act: -0.0000

Data Index: 1198033 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.6318. Min Act: -0.0000

Data Index: 592576 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.0961. Min Act: -0.0000

Data Index: 1823188 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.4901. Min Act: -0.0000

Data Index: 291191 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.1525. Min Act: -0.0000

Data Index: 1914510 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.4879. Min Act: -0.0000

Data Index: 1868877 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.9519. Min Act: -0.0000

Data Index: 1110465 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.7694. Min Act: -0.0000

Data Index: 1411177 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.4937. Min Act: -0.0000

Data Index: 902361 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.7329. Min Act: -0.0000

Data Index: 1648892 (The Pile)

Max Activating Token Index: 196

Text #15

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.2412. Min Act: -0.0000

Data Index: 494919 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.6799. Min Act: -0.0000

Data Index: 315559 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.6372. Min Act: -0.0000

Data Index: 1745934 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.7833. Min Act: -0.0000

Data Index: 399992 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.2236. Min Act: -0.0000

Data Index: 1747735 (The Pile)

Max Activating Token Index: 582