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

Dataset: The Pile

Neuron 579 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: 1.1462. Min Range: -1.1462

Max Act: 1.1462. Min Act: -0.0000

Data Index: 792312 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0762. Min Act: -0.0000

Data Index: 127793 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0604. Min Act: -0.0000

Data Index: 187213 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9742. Min Act: -0.0000

Data Index: 734416 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1445908 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1950505 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1920684 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1928026 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9850. Min Act: -0.0000

Data Index: 838496 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1904136 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9449. Min Act: -0.0000

Data Index: 118265 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9714. Min Act: -0.0000

Data Index: 649330 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1495616 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8589. Min Act: -0.0000

Data Index: 38256 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1000556 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9106. Min Act: -0.0000

Data Index: 38678 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9144. Min Act: -0.0000

Data Index: 952150 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1558049 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1129163 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1723634 (The Pile)

Max Activating Token Index: 291