< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 63 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 2.2323. Min Range: -2.2323

Max Act: 2.2323. Min Act: -0.0000

Data Index: 634694 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2323. Min Range: -2.2323

Max Act: 2.2168. Min Act: -0.0000

Data Index: 707121 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2323. Min Range: -2.2323

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1834229 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2323. Min Range: -2.2323

Max Act: 2.0457. Min Act: -0.0000

Data Index: 1252632 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1096969 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2323. Min Range: -2.2323

Max Act: 2.0159. Min Act: -0.0000

Data Index: 452335 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.8648. Min Act: -0.0000

Data Index: 756394 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1095180 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.8507. Min Act: -0.0000

Data Index: 88246 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.7201. Min Act: -0.0000

Data Index: 1288845 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.9172. Min Act: -0.0000

Data Index: 36048 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.8013. Min Act: -0.0000

Data Index: 190915 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.4888. Min Act: -0.0000

Data Index: 1537188 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.4562. Min Act: -0.0000

Data Index: 483147 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1043998 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.5475. Min Act: -0.0000

Data Index: 1402675 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.3672. Min Act: -0.0000

Data Index: 668629 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1117624 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1190435 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2323. Min Range: -2.2323

Max Act: 1.0849. Min Act: -0.0000

Data Index: 608894 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #19