< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5103 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: 1.5163. Min Range: -1.5163

Max Act: 1.5163. Min Act: -0.0001

Data Index: 29247 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.3664. Min Act: -0.0001

Data Index: 1778633 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0783. Min Act: -0.0001

Data Index: 441525 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0765. Min Act: -0.0001

Data Index: 165917 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1141. Min Act: -0.0001

Data Index: 1209214 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.4021. Min Act: -0.0001

Data Index: 1283058 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1014. Min Act: -0.0001

Data Index: 321481 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1702. Min Act: -0.0001

Data Index: 1528309 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1558403 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1546. Min Act: -0.0001

Data Index: 1665620 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0911. Min Act: -0.0001

Data Index: 881163 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.3221. Min Act: -0.0001

Data Index: 1230517 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0106. Min Act: -0.0001

Data Index: 702735 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1160. Min Act: -0.0001

Data Index: 1857035 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0019. Min Act: -0.0001

Data Index: 1317930 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1068. Min Act: -0.0001

Data Index: 1412880 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1161. Min Act: -0.0001

Data Index: 1398431 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0839. Min Act: -0.0001

Data Index: 371154 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8443. Min Act: -0.0001

Data Index: 1339845 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1545. Min Act: -0.0001

Data Index: 491581 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #19