< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3000 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0001

Data Index: 1040890 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6033. Min Act: -0.0001

Data Index: 513836 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6059. Min Act: -0.0001

Data Index: 419069 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1667640 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5888. Min Act: -0.0001

Data Index: 247208 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5832. Min Act: -0.0001

Data Index: 1328172 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1752923 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5762. Min Act: -0.0001

Data Index: 893772 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1405666 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5522. Min Act: -0.0000

Data Index: 510333 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5729. Min Act: -0.0000

Data Index: 234647 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1058742 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5620. Min Act: -0.0001

Data Index: 910779 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5277. Min Act: -0.0001

Data Index: 1202583 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1232285 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5370. Min Act: -0.0001

Data Index: 41719 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5511. Min Act: -0.0001

Data Index: 887415 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5321. Min Act: -0.0000

Data Index: 293941 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1848279 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5283. Min Act: -0.0001

Data Index: 598562 (The Pile)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #19