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

Dataset: The Pile

Neuron 4745 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.8648. Min Act: -0.0000

Data Index: 137268 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5616. Min Act: -0.0000

Data Index: 130907 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.6822. Min Act: 0.0000

Data Index: 992338 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5758. Min Act: -0.0000

Data Index: 355620 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5695. Min Act: -0.0000

Data Index: 956310 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4623. Min Act: -0.0000

Data Index: 187692 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1543183 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1930387 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5484. Min Act: -0.0000

Data Index: 1849382 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5204. Min Act: -0.0000

Data Index: 216157 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3237. Min Act: -0.0000

Data Index: 262710 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3885. Min Act: -0.0000

Data Index: 14378 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3832. Min Act: -0.0000

Data Index: 64623 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1044704 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4378. Min Act: -0.0000

Data Index: 392844 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.2892. Min Act: -0.0000

Data Index: 169554 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1377582 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1674757 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1112391 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4077. Min Act: -0.0000

Data Index: 1369096 (The Pile)

Max Activating Token Index: 843