< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 48 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.9071. Min Act: -0.0001

Data Index: 1873217 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8405. Min Act: -0.0001

Data Index: 1477474 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1824783 (The Pile)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8119. Min Act: -0.0001

Data Index: 1673380 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8768. Min Act: -0.0001

Data Index: 1479950 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8698. Min Act: -0.0001

Data Index: 1714904 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7119. Min Act: -0.0001

Data Index: 104229 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7829. Min Act: -0.0001

Data Index: 1759758 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7788. Min Act: -0.0001

Data Index: 822895 (The Pile)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7460. Min Act: -0.0001

Data Index: 1529385 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7329. Min Act: -0.0001

Data Index: 1906408 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7302. Min Act: -0.0001

Data Index: 1321979 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8225. Min Act: -0.0001

Data Index: 1819700 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7023. Min Act: -0.0001

Data Index: 860359 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1417182 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7398. Min Act: -0.0001

Data Index: 979499 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7084. Min Act: -0.0001

Data Index: 1186040 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7333. Min Act: -0.0001

Data Index: 71305 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7318. Min Act: -0.0001

Data Index: 234035 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7515. Min Act: -0.0001

Data Index: 1958566 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #19