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

Dataset: The Pile

Neuron 1143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1804527 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0000

Data Index: 638700 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1444108 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0743. Min Act: -0.0000

Data Index: 110555 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1353360 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0706. Min Act: -0.0000

Data Index: 616763 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0625. Min Act: -0.0000

Data Index: 303021 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1258983 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0669. Min Act: -0.0000

Data Index: 395928 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1069908 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0693. Min Act: -0.0000

Data Index: 190148 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1248289 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1713339 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0624. Min Act: 0.0000

Data Index: 901538 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0614. Min Act: -0.0000

Data Index: 230927 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1611801 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1617605 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0603. Min Act: -0.0000

Data Index: 65469 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1728882 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1329526 (The Pile)

Max Activating Token Index: 597