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

Dataset: The Pile

Neuron 529 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: 3.4875. Min Range: -3.4875

Max Act: 3.4875. Min Act: -0.0000

Data Index: 1632548 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.7761. Min Act: -0.0000

Data Index: 1601783 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.8777. Min Act: -0.0000

Data Index: 945399 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.6037. Min Act: -0.0000

Data Index: 1329252 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.2411. Min Act: -0.0000

Data Index: 1758276 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.3378. Min Act: -0.0000

Data Index: 596402 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.1556. Min Act: -0.0000

Data Index: 571877 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1594123 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1747985 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.9878. Min Act: -0.0000

Data Index: 397702 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.3332. Min Act: -0.0000

Data Index: 1549776 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.0636. Min Act: -0.0000

Data Index: 171807 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.9524. Min Act: -0.0000

Data Index: 1949329 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.7891. Min Act: -0.0000

Data Index: 302062 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.6987. Min Act: -0.0000

Data Index: 705427 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 3.4875. Min Range: -3.4875

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1926506 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.9189. Min Act: -0.0000

Data Index: 47059 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.6901. Min Act: -0.0000

Data Index: 964063 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1213226 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 3.4875. Min Range: -3.4875

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1978771 (The Pile)

Max Activating Token Index: 444