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

Dataset: The Pile

Neuron 1879 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: 3.9894. Min Range: -3.9894

Max Act: 3.9894. Min Act: -0.0000

Data Index: 1790126 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 3.9894. Min Range: -3.9894

Max Act: 3.5954. Min Act: -0.0000

Data Index: 153432 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 3.9894. Min Range: -3.9894

Max Act: 3.3565. Min Act: -0.0000

Data Index: 1207518 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 3.9894. Min Range: -3.9894

Max Act: 3.3525. Min Act: -0.0000

Data Index: 669409 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.9361. Min Act: -0.0000

Data Index: 1468638 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 3.9894. Min Range: -3.9894

Max Act: 3.1142. Min Act: -0.0000

Data Index: 253752 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 3.9894. Min Range: -3.9894

Max Act: 3.0055. Min Act: -0.0000

Data Index: 509593 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.7758. Min Act: -0.0000

Data Index: 1896577 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.6509. Min Act: -0.0000

Data Index: 1413256 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.9461. Min Act: -0.0000

Data Index: 1586731 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.5697. Min Act: -0.0000

Data Index: 1617945 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.7467. Min Act: -0.0000

Data Index: 1949574 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.5418. Min Act: -0.0000

Data Index: 441453 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.6380. Min Act: -0.0000

Data Index: 1460253 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.5734. Min Act: -0.0000

Data Index: 1732686 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.5439. Min Act: -0.0000

Data Index: 871265 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.4262. Min Act: -0.0000

Data Index: 1135330 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.5433. Min Act: -0.0000

Data Index: 1668963 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.2974. Min Act: -0.0000

Data Index: 1647981 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 3.9894. Min Range: -3.9894

Max Act: 2.6999. Min Act: -0.0000

Data Index: 312750 (The Pile)

Max Activating Token Index: 725