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

Dataset: The Pile

Neuron 192 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: 0.1868. Min Range: -0.1868

Max Act: 0.1868. Min Act: -0.0000

Data Index: 55921 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1749. Min Act: -0.0000

Data Index: 623980 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1856. Min Act: -0.0000

Data Index: 337673 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1235944 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1496588 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1657. Min Act: -0.0000

Data Index: 132029 (The Pile)

Max Activating Token Index: 68

Text #6

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1591. Min Act: -0.0000

Data Index: 112836 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1401743 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1556. Min Act: -0.0000

Data Index: 649791 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1539. Min Act: -0.0000

Data Index: 207255 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1067885 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1544232 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1619. Min Act: -0.0000

Data Index: 566125 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1690090 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1442. Min Act: -0.0000

Data Index: 441231 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1384. Min Act: -0.0000

Data Index: 766718 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1428. Min Act: -0.0000

Data Index: 413173 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1039304 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1423. Min Act: -0.0000

Data Index: 225818 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1823363 (The Pile)

Max Activating Token Index: 254