< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 50 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: 0.9508. Min Range: -0.9508

Max Act: 0.9508. Min Act: -0.0001

Data Index: 1591062 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1800738 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7535. Min Act: -0.0001

Data Index: 1705209 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7699. Min Act: -0.0001

Data Index: 654321 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7665. Min Act: -0.0001

Data Index: 342257 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7140. Min Act: -0.0001

Data Index: 18518 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6830. Min Act: -0.0001

Data Index: 362575 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7123. Min Act: -0.0001

Data Index: 1044884 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6868. Min Act: -0.0001

Data Index: 483952 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6953. Min Act: -0.0001

Data Index: 232257 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6449. Min Act: -0.0001

Data Index: 649877 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6666. Min Act: -0.0001

Data Index: 852941 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6511. Min Act: -0.0001

Data Index: 327121 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6689. Min Act: -0.0001

Data Index: 277197 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6455. Min Act: -0.0001

Data Index: 911197 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6662. Min Act: -0.0001

Data Index: 1024635 (The Pile)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6464. Min Act: -0.0001

Data Index: 80914 (The Pile)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1720230 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6475. Min Act: -0.0002

Data Index: 20402 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6619. Min Act: -0.0001

Data Index: 1349723 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #19