< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 18 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3150. Min Range: -2.3150

Max Act: 2.3150. Min Act: -0.0000

Data Index: 1053914 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3150. Min Range: -2.3150

Max Act: 2.1899. Min Act: -0.0000

Data Index: 780443 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.8838. Min Act: -0.0000

Data Index: 266253 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.9007. Min Act: -0.0000

Data Index: 1820128 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.7051. Min Act: -0.0000

Data Index: 541612 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1068100 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.6306. Min Act: -0.0000

Data Index: 575043 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1807819 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.6910. Min Act: -0.0000

Data Index: 1975842 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.7089. Min Act: -0.0000

Data Index: 1113595 (The Pile)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.4738. Min Act: -0.0000

Data Index: 786270 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.7891. Min Act: -0.0000

Data Index: 659579 (The Pile)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1180326 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.7350. Min Act: -0.0000

Data Index: 1056996 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1392045 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.6142. Min Act: -0.0000

Data Index: 1520357 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.4914. Min Act: -0.0000

Data Index: 456078 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.4702. Min Act: -0.0000

Data Index: 653624 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.4435. Min Act: -0.0000

Data Index: 829951 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3150. Min Range: -2.3150

Max Act: 1.3902. Min Act: -0.0000

Data Index: 97719 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #19