< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 50 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1930767 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8668. Min Act: -0.0001

Data Index: 443865 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9797. Min Act: -0.0001

Data Index: 1691487 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0181. Min Act: -0.0001

Data Index: 164377 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1249774 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1264984 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1412670 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8421. Min Act: -0.0001

Data Index: 201577 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1122634 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7436. Min Act: -0.0001

Data Index: 1169794 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7680. Min Act: -0.0001

Data Index: 68081 (The Pile)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7266. Min Act: -0.0001

Data Index: 96360 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7490. Min Act: -0.0001

Data Index: 1285736 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1931370 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7103. Min Act: -0.0001

Data Index: 554276 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.6829. Min Act: -0.0001

Data Index: 605064 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7302. Min Act: -0.0001

Data Index: 1076522 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.7515. Min Act: -0.0001

Data Index: 4032 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.6865. Min Act: -0.0001

Data Index: 1230510 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.6798. Min Act: -0.0001

Data Index: 841751 (The Pile)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #19