< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 41 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.5687. Min Act: -0.0001

Data Index: 330957 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3734. Min Act: -0.0001

Data Index: 1832404 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.2879. Min Act: -0.0001

Data Index: 1170137 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3822. Min Act: -0.0001

Data Index: 1232484 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1687. Min Act: -0.0001

Data Index: 642977 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1805. Min Act: -0.0001

Data Index: 685036 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1580. Min Act: -0.0001

Data Index: 1709221 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.2240. Min Act: -0.0001

Data Index: 1271654 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1248. Min Act: -0.0001

Data Index: 1879143 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0287. Min Act: -0.0001

Data Index: 1925759 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9472. Min Act: -0.0001

Data Index: 573957 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0843. Min Act: -0.0001

Data Index: 1171200 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0713. Min Act: -0.0001

Data Index: 1981872 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3139. Min Act: -0.0001

Data Index: 861333 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0997. Min Act: -0.0001

Data Index: 576759 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.2215. Min Act: -0.0001

Data Index: 1422965 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0902. Min Act: -0.0001

Data Index: 1167239 (The Pile)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1250. Min Act: -0.0001

Data Index: 1663245 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1877676 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1037. Min Act: -0.0001

Data Index: 1252394 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #19