< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 17 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.7111. Min Act: -0.0001

Data Index: 1605774 (The Pile)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5993. Min Act: -0.0001

Data Index: 1137775 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5730. Min Act: -0.0001

Data Index: 1652721 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1048410 (The Pile)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1576368 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5522. Min Act: -0.0000

Data Index: 900354 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5669. Min Act: -0.0001

Data Index: 1668773 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5216. Min Act: -0.0001

Data Index: 1287954 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1240659 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5205. Min Act: -0.0001

Data Index: 62857 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5225. Min Act: -0.0001

Data Index: 850285 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5453. Min Act: -0.0000

Data Index: 313661 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5037. Min Act: -0.0001

Data Index: 1318261 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4991. Min Act: 0.0004

Data Index: 964775 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1794295 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5383. Min Act: -0.0001

Data Index: 1824853 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5043. Min Act: 0.0001

Data Index: 928353 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5062. Min Act: -0.0001

Data Index: 508238 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4972. Min Act: -0.0001

Data Index: 911337 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5325. Min Act: -0.0001

Data Index: 1285541 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #19