< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 25 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5765. Min Act: -0.0001

Data Index: 1700905 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5481. Min Act: -0.0001

Data Index: 640873 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5953. Min Act: -0.0001

Data Index: 803936 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.6363. Min Act: -0.0001

Data Index: 327433 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5411. Min Act: -0.0001

Data Index: 503839 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1149012 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1523887 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5646. Min Act: -0.0001

Data Index: 454717 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5593. Min Act: -0.0001

Data Index: 951731 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1650702 (The Pile)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5536. Min Act: -0.0001

Data Index: 734079 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5026. Min Act: -0.0001

Data Index: 1080428 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4972. Min Act: -0.0001

Data Index: 710531 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4992. Min Act: -0.0001

Data Index: 206660 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5243. Min Act: -0.0001

Data Index: 1203065 (The Pile)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5461. Min Act: -0.0001

Data Index: 509908 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5181. Min Act: -0.0001

Data Index: 209108 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.6193. Min Act: -0.0001

Data Index: 1291110 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4993. Min Act: -0.0001

Data Index: 147477 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4820. Min Act: -0.0001

Data Index: 1951954 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #19