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

Dataset: The Pile

Neuron 224 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1819. Min Range: -6.1819

Max Act: 6.1528. Min Act: -0.0000

Data Index: 1154141 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.9818. Min Act: -0.0000

Data Index: 1127198 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 6.1819. Min Range: -6.1819

Max Act: 6.1819. Min Act: -0.0000

Data Index: 324760 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.7490. Min Act: -0.0000

Data Index: 732549 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.7617. Min Act: -0.0000

Data Index: 335112 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.7659. Min Act: -0.0000

Data Index: 846056 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.7647. Min Act: -0.0000

Data Index: 230762 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.7455. Min Act: -0.0000

Data Index: 1533787 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.7321. Min Act: -0.0000

Data Index: 67888 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.6047. Min Act: -0.0000

Data Index: 1737193 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.6196. Min Act: -0.0000

Data Index: 1807330 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.5636. Min Act: -0.0000

Data Index: 857981 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.4923. Min Act: -0.0000

Data Index: 704877 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.6183. Min Act: -0.0000

Data Index: 1895397 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.2753. Min Act: -0.0000

Data Index: 1820081 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.4100. Min Act: -0.0000

Data Index: 261014 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.3996. Min Act: -0.0000

Data Index: 1060054 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.0936. Min Act: -0.0000

Data Index: 207309 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.4550. Min Act: -0.0000

Data Index: 1966102 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 6.1819. Min Range: -6.1819

Max Act: 5.0906. Min Act: -0.0000

Data Index: 1910634 (The Pile)

Max Activating Token Index: 345