< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3046 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: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0001

Data Index: 1377897 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6207. Min Act: -0.0001

Data Index: 1242520 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5472. Min Act: -0.0001

Data Index: 333711 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5132. Min Act: -0.0001

Data Index: 198640 (The Pile)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1130232 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5180. Min Act: -0.0001

Data Index: 1149632 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5291. Min Act: -0.0001

Data Index: 1608853 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1092812 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4619. Min Act: -0.0001

Data Index: 500104 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1882432 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4818. Min Act: -0.0001

Data Index: 985915 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4515. Min Act: -0.0001

Data Index: 1682317 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4736. Min Act: -0.0001

Data Index: 886116 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4685. Min Act: -0.0001

Data Index: 348000 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4358. Min Act: -0.0001

Data Index: 16547 (The Pile)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1805946 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4317. Min Act: -0.0001

Data Index: 539706 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4540. Min Act: -0.0001

Data Index: 1813873 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4406. Min Act: -0.0001

Data Index: 1776081 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4394. Min Act: -0.0001

Data Index: 998726 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #19