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

Dataset: The Pile

Neuron 4768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1338759 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2032. Min Act: -0.0000

Data Index: 830713 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1632929 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2030. Min Act: -0.0000

Data Index: 879249 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1200761 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1996. Min Act: -0.0000

Data Index: 293032 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1898. Min Act: -0.0000

Data Index: 21479 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1939. Min Act: -0.0000

Data Index: 253370 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1016143 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1750. Min Act: -0.0000

Data Index: 614231 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1474. Min Act: -0.0000

Data Index: 595385 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1688567 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1892473 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1989874 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1344189 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1658686 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1609823 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1651. Min Act: -0.0000

Data Index: 817848 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1416. Min Act: -0.0000

Data Index: 423831 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1851208 (The Pile)

Max Activating Token Index: 449