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

Dataset: The Pile

Neuron 2259 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: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0000

Data Index: 115499 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1841461 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1455177 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0827. Min Act: -0.0000

Data Index: 609243 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0763. Min Act: -0.0000

Data Index: 63132 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0850. Min Act: -0.0000

Data Index: 633874 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1396900 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1752013 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0721. Min Act: -0.0000

Data Index: 159624 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1662714 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1122928 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1788913 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0741. Min Act: -0.0000

Data Index: 389031 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0706. Min Act: -0.0000

Data Index: 171767 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1445685 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1410955 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0701. Min Act: -0.0000

Data Index: 106553 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1728190 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0675. Min Act: -0.0000

Data Index: 329374 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1759661 (The Pile)

Max Activating Token Index: 603