< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4035 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: 2.0624. Min Range: -2.0624

Max Act: 2.0624. Min Act: -0.0001

Data Index: 1307716 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.9605. Min Act: -0.0001

Data Index: 773085 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0624. Min Range: -2.0624

Max Act: 2.0302. Min Act: -0.0001

Data Index: 286546 (The Pile)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7870. Min Act: -0.0001

Data Index: 286377 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7830. Min Act: -0.0001

Data Index: 1078499 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7504. Min Act: -0.0001

Data Index: 756394 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.8215. Min Act: -0.0001

Data Index: 529986 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.8041. Min Act: -0.0001

Data Index: 766053 (The Pile)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.8094. Min Act: -0.0001

Data Index: 832310 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7947. Min Act: -0.0001

Data Index: 1459208 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7934. Min Act: -0.0001

Data Index: 1093581 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7561. Min Act: -0.0001

Data Index: 1847006 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.9540. Min Act: -0.0001

Data Index: 1903649 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7522. Min Act: -0.0001

Data Index: 1741708 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.6567. Min Act: -0.0001

Data Index: 1439067 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.8394. Min Act: -0.0001

Data Index: 1639235 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7210. Min Act: -0.0001

Data Index: 1657686 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.6868. Min Act: -0.0001

Data Index: 1102629 (The Pile)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7343. Min Act: -0.0001

Data Index: 698378 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0624. Min Range: -2.0624

Max Act: 1.7416. Min Act: -0.0001

Data Index: 1525803 (The Pile)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #19