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

Dataset: The Pile

Neuron 571 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: 1.0728. Min Range: -1.0728

Max Act: 1.0728. Min Act: -0.0000

Data Index: 686275 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1731426 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1256020 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.8132. Min Act: -0.0000

Data Index: 890292 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1111394 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1600110 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7769. Min Act: -0.0000

Data Index: 99797 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1743450 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1608844 (The Pile)

Max Activating Token Index: 344

Text #9

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1383298 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1551235 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1302702 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1956138 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1118913 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.7542. Min Act: 0.0000

Data Index: 369544 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.6921. Min Act: -0.0000

Data Index: 70198 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.6019. Min Act: -0.0000

Data Index: 274079 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1000060 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.5998. Min Act: -0.0000

Data Index: 688131 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 1.0728. Min Range: -1.0728

Max Act: 0.6575. Min Act: -0.0000

Data Index: 462630 (The Pile)

Max Activating Token Index: 757