< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 30 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1920935 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0824. Min Act: -0.0002

Data Index: 965332 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0786. Min Act: -0.0002

Data Index: 260072 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0715. Min Act: -0.0003

Data Index: 798043 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1629296 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1731364 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1440890 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1922051 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1857285 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0660. Min Act: -0.0002

Data Index: 901087 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0641. Min Act: -0.0002

Data Index: 84476 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1294078 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1801700 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1170143 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0561. Min Act: -0.0003

Data Index: 90004 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1533435 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0552. Min Act: -0.0002

Data Index: 723300 (The Pile)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1470709 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1313022 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0532. Min Act: -0.0002

Data Index: 123782 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #19