< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 12 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.9514. Min Act: -0.0001

Data Index: 1452913 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.9305. Min Act: -0.0001

Data Index: 1569839 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8385. Min Act: -0.0001

Data Index: 364820 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.9245. Min Act: -0.0001

Data Index: 659759 (The Pile)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8845. Min Act: -0.0001

Data Index: 367976 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8779. Min Act: -0.0001

Data Index: 646159 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8681. Min Act: -0.0001

Data Index: 1952300 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7997. Min Act: -0.0001

Data Index: 1478677 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8414. Min Act: -0.0001

Data Index: 800083 (The Pile)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8253. Min Act: -0.0001

Data Index: 180011 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8405. Min Act: -0.0001

Data Index: 887800 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8754. Min Act: -0.0001

Data Index: 107048 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8193. Min Act: -0.0001

Data Index: 618082 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8171. Min Act: -0.0001

Data Index: 1923697 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8068. Min Act: -0.0001

Data Index: 220209 (The Pile)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8047. Min Act: -0.0001

Data Index: 40675 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1074392 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7762. Min Act: -0.0001

Data Index: 662002 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8596. Min Act: -0.0001

Data Index: 658264 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1909315 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #19