< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.1342. Min Range: -1.1342

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1155581 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1342. Min Range: -1.1342

Max Act: 1.1342. Min Act: -0.0001

Data Index: 111810 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9787. Min Act: -0.0001

Data Index: 447153 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9996. Min Act: -0.0000

Data Index: 875559 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9924. Min Act: -0.0001

Data Index: 306452 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1187834 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1501670 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1032009 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8460. Min Act: -0.0001

Data Index: 1584952 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1064001 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9190. Min Act: -0.0001

Data Index: 1600855 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7884. Min Act: -0.0001

Data Index: 189537 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9171. Min Act: -0.0001

Data Index: 1699247 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8480. Min Act: -0.0001

Data Index: 1312597 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1375235 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8825. Min Act: -0.0001

Data Index: 1492151 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1846165 (The Pile)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8149. Min Act: -0.0000

Data Index: 472190 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1750943 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1426849 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #19