< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 53 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0001

Data Index: 686683 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1558387 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1751423 (The Pile)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1888152 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0495. Min Act: -0.0002

Data Index: 740233 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0422. Min Act: -0.0002

Data Index: 421191 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1102999 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1008680 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0430. Min Act: -0.0001

Data Index: 909394 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1249269 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0001

Data Index: 682567 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0001

Data Index: 929647 (The Pile)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0001

Data Index: 787510 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0001

Data Index: 265183 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0473. Min Act: -0.0001

Data Index: 659736 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1960877 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0376. Min Act: -0.0001

Data Index: 531430 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1459176 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0403. Min Act: -0.0001

Data Index: 9134 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0420. Min Act: -0.0001

Data Index: 95828 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #19