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

Dataset: The Pile

Neuron 1781 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: 0.6636. Min Range: -0.6636

Max Act: 0.6636. Min Act: -0.0000

Data Index: 528730 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1318207 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1539628 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1446255 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4525. Min Act: -0.0000

Data Index: 522800 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4895. Min Act: -0.0000

Data Index: 187494 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1300186 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1337048 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1927021 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1133494 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4635. Min Act: -0.0000

Data Index: 902421 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1520141 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1566334 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1301594 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1045699 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1345806 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4655. Min Act: -0.0000

Data Index: 739337 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1382052 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4045. Min Act: -0.0000

Data Index: 275792 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4732. Min Act: -0.0000

Data Index: 976552 (The Pile)

Max Activating Token Index: 950