< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 14 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: 1.5754. Min Range: -1.5754

Max Act: 1.5474. Min Act: -0.0001

Data Index: 666179 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.5754. Min Act: -0.0001

Data Index: 1208633 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.4508. Min Act: -0.0001

Data Index: 916342 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.4314. Min Act: -0.0001

Data Index: 133540 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.4221. Min Act: -0.0001

Data Index: 1451611 (The Pile)

Max Activating Token Index: 97

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.4432. Min Act: -0.0001

Data Index: 1636815 (The Pile)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.3580. Min Act: -0.0001

Data Index: 1427865 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.3814. Min Act: -0.0001

Data Index: 1309386 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.3353. Min Act: -0.0001

Data Index: 211213 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2915. Min Act: -0.0001

Data Index: 127621 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2608. Min Act: -0.0001

Data Index: 767458 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2911. Min Act: -0.0001

Data Index: 317745 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.3048. Min Act: -0.0001

Data Index: 734388 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2790. Min Act: -0.0001

Data Index: 1433615 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2737. Min Act: -0.0001

Data Index: 1973984 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2659. Min Act: -0.0001

Data Index: 435431 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2849. Min Act: -0.0001

Data Index: 793582 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2900. Min Act: -0.0001

Data Index: 1330246 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2645. Min Act: -0.0001

Data Index: 806508 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5754. Min Range: -1.5754

Max Act: 1.2542. Min Act: -0.0001

Data Index: 477617 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19