< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 21 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.0611. Min Range: -1.0611

Max Act: 1.0092. Min Act: -0.0002

Data Index: 1900079 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0611. Min Range: -1.0611

Max Act: 1.0611. Min Act: -0.0002

Data Index: 1914640 (The Pile)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9773. Min Act: -0.0002

Data Index: 1835742 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9403. Min Act: -0.0001

Data Index: 1785619 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0611. Min Range: -1.0611

Max Act: 1.0152. Min Act: -0.0001

Data Index: 254739 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9503. Min Act: -0.0002

Data Index: 1345534 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9607. Min Act: -0.0002

Data Index: 1472833 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9028. Min Act: -0.0002

Data Index: 1524189 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8847. Min Act: -0.0002

Data Index: 863905 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9545. Min Act: -0.0001

Data Index: 1865104 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8702. Min Act: -0.0002

Data Index: 410050 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9205. Min Act: -0.0002

Data Index: 704871 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1377463 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8178. Min Act: -0.0001

Data Index: 1712505 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7795. Min Act: -0.0002

Data Index: 1684364 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8304. Min Act: -0.0002

Data Index: 706281 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8320. Min Act: -0.0002

Data Index: 1409960 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8799. Min Act: -0.0002

Data Index: 346839 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8743. Min Act: -0.0002

Data Index: 292571 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9512. Min Act: -0.0002

Data Index: 1999539 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #19