< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 30 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3630. Min Range: -2.3630

Max Act: 2.2817. Min Act: -0.0000

Data Index: 402551 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3630. Min Range: -2.3630

Max Act: 2.3630. Min Act: 0.0000

Data Index: 895431 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3630. Min Range: -2.3630

Max Act: 2.3538. Min Act: -0.0000

Data Index: 242740 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3630. Min Range: -2.3630

Max Act: 2.1878. Min Act: 0.0000

Data Index: 1425899 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.9556. Min Act: 0.0000

Data Index: 404097 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.8958. Min Act: 0.0000

Data Index: 379337 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3630. Min Range: -2.3630

Max Act: 2.1236. Min Act: 0.0001

Data Index: 1985335 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.8992. Min Act: 0.0000

Data Index: 115388 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.8096. Min Act: -0.0000

Data Index: 63267 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.8847. Min Act: 0.0001

Data Index: 1405634 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.7574. Min Act: 0.0000

Data Index: 1149358 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.7261. Min Act: 0.0000

Data Index: 1172006 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1592029 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.7990. Min Act: 0.0000

Data Index: 762018 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.7262. Min Act: 0.0000

Data Index: 1580311 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.6926. Min Act: 0.0000

Data Index: 1476306 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.7638. Min Act: 0.0001

Data Index: 980649 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.6637. Min Act: 0.0000

Data Index: 326480 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.8589. Min Act: 0.0001

Data Index: 362529 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3630. Min Range: -2.3630

Max Act: 1.6496. Min Act: 0.0000

Data Index: 1988140 (The Pile)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #19