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

Dataset: The Pile

Neuron 2793 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1100798 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1817. Min Act: -0.0000

Data Index: 10649 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1503728 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9903. Min Act: -0.0000

Data Index: 508314 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0418. Min Act: -0.0000

Data Index: 428470 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1767589 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1296518 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1008935 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9962. Min Act: -0.0000

Data Index: 415851 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9400. Min Act: -0.0000

Data Index: 164087 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8850. Min Act: -0.0000

Data Index: 441324 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8703. Min Act: -0.0000

Data Index: 734959 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8991. Min Act: -0.0000

Data Index: 763183 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1852994 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8991. Min Act: -0.0000

Data Index: 991222 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8673. Min Act: -0.0000

Data Index: 439096 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1315896 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1675201 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8564. Min Act: -0.0000

Data Index: 275353 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8081. Min Act: -0.0000

Data Index: 913852 (The Pile)

Max Activating Token Index: 647