< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4092 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0634. Min Act: -0.0001

Data Index: 867982 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.1793. Min Act: -0.0001

Data Index: 536361 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0745. Min Act: -0.0001

Data Index: 1870833 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9550. Min Act: -0.0001

Data Index: 25622 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9958. Min Act: -0.0001

Data Index: 1572892 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0351. Min Act: -0.0001

Data Index: 924227 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0308. Min Act: -0.0001

Data Index: 1830903 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0187. Min Act: -0.0001

Data Index: 328591 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8534. Min Act: -0.0001

Data Index: 1251496 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8194. Min Act: -0.0001

Data Index: 1327557 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9261. Min Act: -0.0001

Data Index: 637912 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9005. Min Act: -0.0001

Data Index: 1469431 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9173. Min Act: -0.0001

Data Index: 156603 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8353. Min Act: -0.0001

Data Index: 689512 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8353. Min Act: -0.0001

Data Index: 1854393 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8040. Min Act: -0.0001

Data Index: 285257 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.7996. Min Act: -0.0001

Data Index: 579096 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9464. Min Act: -0.0001

Data Index: 1574565 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8505. Min Act: -0.0001

Data Index: 249480 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0729. Min Act: -0.0001

Data Index: 1460716 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #19