< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 18 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.2025. Min Act: -0.0001

Data Index: 887681 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1318551 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1855. Min Act: -0.0001

Data Index: 1237394 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1217410 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1428185 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1272555 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1687493 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1701. Min Act: -0.0000

Data Index: 606998 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1644. Min Act: -0.0000

Data Index: 69795 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1565. Min Act: -0.0000

Data Index: 316842 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1476011 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1680. Min Act: -0.0001

Data Index: 950635 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1577. Min Act: -0.0000

Data Index: 453118 (The Pile)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1319683 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1948838 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1510. Min Act: -0.0001

Data Index: 695089 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1453268 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1595. Min Act: -0.0000

Data Index: 397559 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1356727 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2025. Min Range: -0.2025

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1131973 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #19