< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 44 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: 1.0301. Min Range: -1.0301

Max Act: 0.8897. Min Act: -0.0001

Data Index: 810892 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.9972. Min Act: -0.0001

Data Index: 1328844 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.9043. Min Act: -0.0001

Data Index: 535788 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0301. Min Range: -1.0301

Max Act: 1.0301. Min Act: -0.0001

Data Index: 836429 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8873. Min Act: -0.0001

Data Index: 121418 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.9280. Min Act: -0.0001

Data Index: 832498 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.9116. Min Act: -0.0001

Data Index: 127172 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8164. Min Act: -0.0001

Data Index: 932141 (The Pile)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8111. Min Act: -0.0001

Data Index: 582687 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8835. Min Act: -0.0001

Data Index: 1278126 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1348796 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1032871 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1745321 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7508. Min Act: -0.0001

Data Index: 926356 (The Pile)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7963. Min Act: -0.0001

Data Index: 415652 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1871767 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8294. Min Act: -0.0001

Data Index: 1661592 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7547. Min Act: -0.0001

Data Index: 745430 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7904. Min Act: -0.0001

Data Index: 887220 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7580. Min Act: -0.0001

Data Index: 969138 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #19