< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3041 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.9017. Min Act: -0.0001

Data Index: 134185 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.7621. Min Act: -0.0001

Data Index: 825304 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.7252. Min Act: -0.0001

Data Index: 155981 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.7164. Min Act: -0.0001

Data Index: 1130049 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.7092. Min Act: -0.0001

Data Index: 46349 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.5937. Min Act: -0.0001

Data Index: 689996 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.5259. Min Act: -0.0001

Data Index: 1710555 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.5547. Min Act: -0.0001

Data Index: 601510 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.4868. Min Act: -0.0001

Data Index: 1300916 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.4987. Min Act: -0.0001

Data Index: 1704461 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.4975. Min Act: -0.0001

Data Index: 1773146 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.3544. Min Act: -0.0001

Data Index: 1687751 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.4002. Min Act: -0.0001

Data Index: 1648112 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.3303. Min Act: -0.0001

Data Index: 573284 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.5621. Min Act: -0.0001

Data Index: 878166 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.3658. Min Act: -0.0001

Data Index: 1433285 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.4438. Min Act: -0.0001

Data Index: 1488087 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.5026. Min Act: -0.0001

Data Index: 1195428 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.3164. Min Act: -0.0001

Data Index: 1350434 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9017. Min Range: -2.9017

Max Act: 2.3700. Min Act: -0.0001

Data Index: 1642636 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #19