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

Dataset: The Pile

Neuron 2405 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: 1.8772. Min Range: -1.8772

Max Act: 1.7855. Min Act: -0.0000

Data Index: 1844469 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.8772. Min Act: -0.0000

Data Index: 1200297 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.7062. Min Act: -0.0000

Data Index: 874570 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6108. Min Act: -0.0000

Data Index: 1096514 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6075. Min Act: -0.0000

Data Index: 1566631 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6753. Min Act: -0.0000

Data Index: 47193 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1184645 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4764. Min Act: -0.0000

Data Index: 827949 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.5223. Min Act: -0.0000

Data Index: 1842114 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.7000. Min Act: -0.0000

Data Index: 767192 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6801. Min Act: -0.0000

Data Index: 502877 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4006. Min Act: -0.0000

Data Index: 1056090 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1218139 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1639728 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.5166. Min Act: -0.0000

Data Index: 486095 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.5071. Min Act: -0.0000

Data Index: 482397 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.6802. Min Act: -0.0000

Data Index: 892714 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4799. Min Act: -0.0000

Data Index: 1408638 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1326051 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 1.8772. Min Range: -1.8772

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1436980 (The Pile)

Max Activating Token Index: 146