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

Dataset: The Pile

Neuron 4689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1794178 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4525. Min Act: -0.0000

Data Index: 233258 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1399902 (The Pile)

Max Activating Token Index: 873

Text #3

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4175. Min Act: -0.0000

Data Index: 124652 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1463937 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1147859 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3908. Min Act: -0.0000

Data Index: 65904 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1239463 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1167670 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1566767 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3377. Min Act: -0.0000

Data Index: 891787 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3178. Min Act: -0.0000

Data Index: 973675 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1832868 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1920520 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1841569 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3548. Min Act: -0.0000

Data Index: 244037 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3184. Min Act: -0.0000

Data Index: 757707 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1753050 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3410. Min Act: -0.0000

Data Index: 747008 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3299. Min Act: -0.0000

Data Index: 521738 (The Pile)

Max Activating Token Index: 322