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

Dataset: The Pile

Neuron 90 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0912. Min Act: -0.0000

Data Index: 159857 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.1004. Min Act: -0.0000

Data Index: 443999 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0911. Min Act: -0.0000

Data Index: 283414 (The Pile)

Max Activating Token Index: 846

Text #3

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0753. Min Act: -0.0000

Data Index: 950374 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1977792 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1584040 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0825. Min Act: -0.0000

Data Index: 206095 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1737721 (The Pile)

Max Activating Token Index: 971

Text #8

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1045177 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0782. Min Act: -0.0000

Data Index: 804906 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1680178 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0743. Min Act: -0.0000

Data Index: 418701 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0763. Min Act: -0.0000

Data Index: 436905 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1403873 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1451425 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0760. Min Act: -0.0000

Data Index: 535469 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1340861 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1747883 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0660. Min Act: -0.0000

Data Index: 930193 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0665. Min Act: -0.0000

Data Index: 678839 (The Pile)

Max Activating Token Index: 353