< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5059 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: 2.1546. Min Range: -2.1546

Max Act: 2.1546. Min Act: -0.0000

Data Index: 1452588 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.7761. Min Act: -0.0000

Data Index: 861439 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.8480. Min Act: -0.0000

Data Index: 457734 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.8044. Min Act: -0.0000

Data Index: 702339 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.7040. Min Act: -0.0000

Data Index: 881044 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1500081 (The Pile)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.8445. Min Act: -0.0000

Data Index: 1404736 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1811247 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.6090. Min Act: -0.0000

Data Index: 389556 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.6706. Min Act: -0.0000

Data Index: 389791 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.6523. Min Act: -0.0000

Data Index: 299354 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1579024 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.5260. Min Act: -0.0000

Data Index: 78142 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.4816. Min Act: -0.0000

Data Index: 534465 (The Pile)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.5424. Min Act: -0.0000

Data Index: 720680 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.6214. Min Act: -0.0000

Data Index: 967134 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.5348. Min Act: -0.0000

Data Index: 630428 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.5018. Min Act: -0.0000

Data Index: 429692 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1152792 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1546. Min Range: -2.1546

Max Act: 1.6563. Min Act: -0.0000

Data Index: 90851 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #19