< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0001

Data Index: 356125 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0001

Data Index: 680873 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0768. Min Act: -0.0001

Data Index: 58849 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0776. Min Act: -0.0002

Data Index: 139180 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1800909 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0698. Min Act: -0.0002

Data Index: 854398 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1231649 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1348952 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0761. Min Act: -0.0002

Data Index: 765570 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0763. Min Act: -0.0002

Data Index: 802236 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1327103 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0755. Min Act: -0.0001

Data Index: 574014 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0723. Min Act: -0.0002

Data Index: 905639 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0746. Min Act: -0.0002

Data Index: 541773 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0651. Min Act: -0.0002

Data Index: 348310 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1922708 (The Pile)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0715. Min Act: -0.0001

Data Index: 538802 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1176744 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0734. Min Act: -0.0002

Data Index: 936007 (The Pile)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0733. Min Act: -0.0002

Data Index: 980288 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #19