< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 76 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: 2.9167. Min Range: -2.9167

Max Act: 2.9167. Min Act: -0.0001

Data Index: 1711376 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.5681. Min Act: -0.0001

Data Index: 1600548 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1728. Min Act: -0.0001

Data Index: 296042 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3676. Min Act: -0.0001

Data Index: 1467043 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3483. Min Act: -0.0001

Data Index: 145230 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3228. Min Act: -0.0001

Data Index: 1857143 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.2975. Min Act: -0.0001

Data Index: 67410 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1807. Min Act: -0.0001

Data Index: 1786943 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3412. Min Act: -0.0001

Data Index: 101582 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1738. Min Act: -0.0001

Data Index: 94950 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.2416. Min Act: -0.0001

Data Index: 15501 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3460. Min Act: -0.0001

Data Index: 1555384 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1937. Min Act: -0.0001

Data Index: 796778 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1526. Min Act: -0.0001

Data Index: 380336 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1126. Min Act: -0.0001

Data Index: 1586620 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.3600. Min Act: -0.0001

Data Index: 1545301 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.8858. Min Act: -0.0001

Data Index: 123918 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9167. Min Range: -2.9167

Max Act: 1.8472. Min Act: -0.0001

Data Index: 1563777 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.2114. Min Act: -0.0001

Data Index: 1446490 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9167. Min Range: -2.9167

Max Act: 2.1674. Min Act: -0.0001

Data Index: 650661 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #19