< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 41 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: 0.1550. Min Range: -0.1550

Max Act: 0.1550. Min Act: -0.0004

Data Index: 1992313 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1494. Min Act: -0.0004

Data Index: 732258 (The Pile)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1453. Min Act: -0.0004

Data Index: 703277 (The Pile)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1457. Min Act: -0.0004

Data Index: 824268 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1443. Min Act: -0.0004

Data Index: 1245990 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1387. Min Act: -0.0004

Data Index: 545597 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1443. Min Act: -0.0004

Data Index: 155983 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1374. Min Act: -0.0004

Data Index: 181420 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1422. Min Act: -0.0004

Data Index: 1725514 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1472. Min Act: -0.0004

Data Index: 661678 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1419. Min Act: -0.0004

Data Index: 936378 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1417. Min Act: -0.0004

Data Index: 1363835 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1409. Min Act: -0.0004

Data Index: 490338 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1409. Min Act: -0.0004

Data Index: 315298 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1397. Min Act: -0.0004

Data Index: 766701 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1385. Min Act: -0.0004

Data Index: 40545 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1389. Min Act: -0.0004

Data Index: 1441830 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1329. Min Act: -0.0004

Data Index: 776625 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1389. Min Act: -0.0004

Data Index: 97571 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1432. Min Act: -0.0004

Data Index: 1816310 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #19