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

Dataset: The Pile

Neuron 1049 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: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1277664 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1031. Min Act: -0.0000

Data Index: 889340 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1149067 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0863. Min Act: -0.0000

Data Index: 87665 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0769. Min Act: -0.0000

Data Index: 479089 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1568506 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0813. Min Act: -0.0000

Data Index: 429814 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0754. Min Act: -0.0000

Data Index: 382118 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0769. Min Act: -0.0000

Data Index: 89389 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1150764 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1021445 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1176884 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0785. Min Act: -0.0000

Data Index: 263680 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0778. Min Act: -0.0000

Data Index: 279326 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1144142 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0780. Min Act: -0.0000

Data Index: 789120 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1521525 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1796175 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0700. Min Act: -0.0000

Data Index: 165756 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1840750 (The Pile)

Max Activating Token Index: 531