< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 71 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5231. Min Act: -0.0004

Data Index: 1766754 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5299. Min Act: -0.0004

Data Index: 1861847 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4757. Min Act: -0.0004

Data Index: 1519706 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5259. Min Act: -0.0004

Data Index: 666887 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5231. Min Act: -0.0004

Data Index: 90606 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5155. Min Act: -0.0004

Data Index: 279343 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5434. Min Act: -0.0004

Data Index: 1119912 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5182. Min Act: -0.0004

Data Index: 1523258 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4969. Min Act: -0.0004

Data Index: 246482 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5127. Min Act: -0.0004

Data Index: 1060149 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4954. Min Act: -0.0004

Data Index: 230882 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4571. Min Act: -0.0004

Data Index: 200580 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5059. Min Act: -0.0004

Data Index: 1495127 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5013. Min Act: -0.0004

Data Index: 1857548 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4992. Min Act: -0.0004

Data Index: 925466 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4623. Min Act: -0.0004

Data Index: 316118 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5155. Min Act: -0.0004

Data Index: 297876 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4933. Min Act: -0.0004

Data Index: 1769964 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4919. Min Act: -0.0004

Data Index: 1717986 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4400. Min Act: -0.0004

Data Index: 1395722 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #19