< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 43 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1402. Min Act: -0.0001

Data Index: 677567 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1560. Min Act: -0.0001

Data Index: 772694 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1790516 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1483. Min Act: -0.0001

Data Index: 465215 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1630365 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1612. Min Act: -0.0001

Data Index: 631775 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1527. Min Act: -0.0001

Data Index: 244026 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1958029 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1079507 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1383. Min Act: -0.0001

Data Index: 384580 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1386. Min Act: -0.0001

Data Index: 170001 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1662912 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1635466 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1540576 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1081707 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1896830 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1310. Min Act: -0.0001

Data Index: 278809 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1431367 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1283543 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1275. Min Act: -0.0001

Data Index: 782565 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #19