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

Dataset: The Pile

Neuron 2929 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: 0.4684. Min Range: -0.4684

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1604809 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1384916 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4510. Min Act: -0.0000

Data Index: 196141 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4178. Min Act: -0.0000

Data Index: 229168 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1681325 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1374291 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1805986 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4147. Min Act: -0.0000

Data Index: 430200 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3964. Min Act: -0.0000

Data Index: 735648 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1421556 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3704. Min Act: -0.0000

Data Index: 929053 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3925. Min Act: -0.0000

Data Index: 217658 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1809147 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3618. Min Act: -0.0000

Data Index: 350044 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3733. Min Act: -0.0000

Data Index: 891020 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3717. Min Act: -0.0000

Data Index: 426125 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1516899 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1756665 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3805. Min Act: -0.0000

Data Index: 636780 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3563. Min Act: -0.0000

Data Index: 605333 (The Pile)

Max Activating Token Index: 764