< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 24 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.5416. Min Act: -0.0000

Data Index: 630239 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1010153 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.4790. Min Act: -0.0000

Data Index: 1762033 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1187678 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1362762 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1692089 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2892. Min Act: -0.0000

Data Index: 359600 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2011. Min Act: -0.0000

Data Index: 474890 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1535166 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1369. Min Act: 0.0000

Data Index: 897644 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1868. Min Act: -0.0000

Data Index: 766999 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1996385 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1562610 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1852932 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1379838 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2447. Min Act: 0.0000

Data Index: 1084535 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1691. Min Act: -0.0000

Data Index: 696035 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1712. Min Act: -0.0000

Data Index: 505926 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.0064. Min Act: -0.0000

Data Index: 983782 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1980390 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #19