Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 194 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2679. Min Act: -0.0000

Data Index: 247276 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2344. Min Act: -0.0000

Data Index: 321551 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2157. Min Act: -0.0000

Data Index: 72660 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1902. Min Act: -0.0000

Data Index: 152270 (The Pile)

Max Activating Token Index: 747

Text #4

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1070387 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1929656 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1582. Min Act: -0.0000

Data Index: 988562 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1789. Min Act: -0.0000

Data Index: 859284 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1797. Min Act: -0.0000

Data Index: 90466 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1757592 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1976411 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1917627 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1896458 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1490635 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1828. Min Act: -0.0000

Data Index: 622546 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1214500 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1616. Min Act: -0.0000

Data Index: 234180 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1596697 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1328710 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1782. Min Act: -0.0000

Data Index: 599225 (The Pile)

Max Activating Token Index: 538