< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1910432 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1295. Min Act: -0.0001

Data Index: 59795 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1256399 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0611. Min Act: -0.0001

Data Index: 883279 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1609223 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1564760 (The Pile)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0563. Min Act: -0.0001

Data Index: 252142 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1846832 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0436. Min Act: -0.0001

Data Index: 588699 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0485. Min Act: -0.0001

Data Index: 384828 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1589561 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0494. Min Act: -0.0001

Data Index: 289904 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0567. Min Act: -0.0000

Data Index: 917843 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1595840 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1950483 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1079507 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0505. Min Act: -0.0001

Data Index: 142024 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1807235 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0468. Min Act: -0.0001

Data Index: 7552 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #19