< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 33 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6778. Min Act: -0.0001

Data Index: 1301178 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1095377 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.7163. Min Act: -0.0001

Data Index: 1083008 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6611. Min Act: -0.0001

Data Index: 1945988 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.7006. Min Act: -0.0001

Data Index: 44591 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.7007. Min Act: -0.0001

Data Index: 1111529 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6314. Min Act: -0.0001

Data Index: 710219 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1379972 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1958148 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6447. Min Act: -0.0001

Data Index: 502269 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5757. Min Act: -0.0001

Data Index: 536298 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5855. Min Act: -0.0001

Data Index: 294691 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5909. Min Act: -0.0001

Data Index: 310690 (The Pile)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6461. Min Act: -0.0001

Data Index: 1630026 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1023905 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5760. Min Act: -0.0001

Data Index: 1012349 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6208. Min Act: -0.0001

Data Index: 501672 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6120. Min Act: -0.0001

Data Index: 1054355 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6121. Min Act: -0.0001

Data Index: 1346242 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6577. Min Act: -0.0001

Data Index: 55468 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #19