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

Dataset: The Pile

Neuron 3899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1779865 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.2225. Min Act: -0.0000

Data Index: 970317 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.2032. Min Act: -0.0000

Data Index: 444591 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1867. Min Act: -0.0000

Data Index: 216201 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1884. Min Act: -0.0000

Data Index: 196082 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1832. Min Act: -0.0000

Data Index: 97641 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1163245 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1722. Min Act: -0.0000

Data Index: 718690 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1624. Min Act: 0.0000

Data Index: 1575325 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1348566 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1723. Min Act: -0.0000

Data Index: 127025 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1317286 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1718642 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1585. Min Act: -0.0000

Data Index: 959197 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1625. Min Act: -0.0000

Data Index: 572558 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1839007 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1518. Min Act: -0.0000

Data Index: 386816 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1836258 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1474. Min Act: -0.0000

Data Index: 335833 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 0.2225. Min Range: -0.2225

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1613719 (The Pile)

Max Activating Token Index: 571