< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1417649 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0939. Min Act: -0.0002

Data Index: 849613 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0925. Min Act: -0.0002

Data Index: 675734 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0925. Min Act: -0.0002

Data Index: 30338 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1690114 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0002

Data Index: 287443 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1383909 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0859. Min Act: -0.0002

Data Index: 621966 (The Pile)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0822. Min Act: -0.0002

Data Index: 219009 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0846. Min Act: -0.0002

Data Index: 541534 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0851. Min Act: -0.0002

Data Index: 504826 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1039598 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1972047 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0814. Min Act: -0.0002

Data Index: 247373 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0805. Min Act: -0.0002

Data Index: 386004 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1279977 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1544041 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0767. Min Act: -0.0002

Data Index: 168987 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1497976 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0762. Min Act: -0.0002

Data Index: 841201 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #19