< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.4734. Min Act: -0.0001

Data Index: 138128 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.8960. Min Act: -0.0001

Data Index: 766006 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.7295. Min Act: -0.0001

Data Index: 160378 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.8009. Min Act: -0.0001

Data Index: 1777478 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.7758. Min Act: -0.0001

Data Index: 1998186 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.7299. Min Act: -0.0001

Data Index: 1491944 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.7350. Min Act: -0.0001

Data Index: 481768 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.7006. Min Act: -0.0001

Data Index: 67734 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.6208. Min Act: -0.0001

Data Index: 1637783 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.8142. Min Act: -0.0001

Data Index: 228102 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.3704. Min Act: -0.0001

Data Index: 1601030 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.6527. Min Act: -0.0001

Data Index: 848329 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.6424. Min Act: -0.0001

Data Index: 1442361 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.6430. Min Act: -0.0001

Data Index: 1714102 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.6308. Min Act: -0.0001

Data Index: 437540 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.5639. Min Act: -0.0001

Data Index: 1379566 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.5706. Min Act: -0.0001

Data Index: 372152 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.5349. Min Act: -0.0001

Data Index: 1617074 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.7358. Min Act: -0.0001

Data Index: 1093658 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8960. Min Range: -2.8960

Max Act: 2.5355. Min Act: -0.0001

Data Index: 1179394 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #19