< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3060 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.5309. Min Act: -0.0001

Data Index: 1864837 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1845469 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1161669 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3665. Min Act: -0.0001

Data Index: 1118185 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3409. Min Act: -0.0001

Data Index: 808348 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3364. Min Act: -0.0001

Data Index: 1864574 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1179399 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3508. Min Act: -0.0001

Data Index: 316174 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3324. Min Act: -0.0001

Data Index: 803983 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1080692 (The Pile)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1782265 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3616. Min Act: 0.0000

Data Index: 213605 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3452. Min Act: -0.0001

Data Index: 451793 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1268422 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1235106 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1214672 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3302. Min Act: -0.0001

Data Index: 1757060 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1075332 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1473114 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1443549 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #19