< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 64 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.3153. Min Range: -4.3153

Max Act: 4.3153. Min Act: -0.0000

Data Index: 748316 (The Pile)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3153. Min Range: -4.3153

Max Act: 3.9500. Min Act: -0.0000

Data Index: 1567313 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3153. Min Range: -4.3153

Max Act: 3.9669. Min Act: -0.0000

Data Index: 559815 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3153. Min Range: -4.3153

Max Act: 3.4590. Min Act: -0.0000

Data Index: 503736 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.9139. Min Act: -0.0000

Data Index: 598888 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.8660. Min Act: -0.0000

Data Index: 1166397 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.8291. Min Act: -0.0000

Data Index: 61033 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.9421. Min Act: -0.0000

Data Index: 388627 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.5211. Min Act: -0.0000

Data Index: 216959 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.7368. Min Act: -0.0000

Data Index: 604380 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.7142. Min Act: -0.0000

Data Index: 1414183 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.9713. Min Act: -0.0000

Data Index: 1760152 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1533570 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.7286. Min Act: -0.0000

Data Index: 1859651 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.3504. Min Act: -0.0000

Data Index: 1770080 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.4062. Min Act: -0.0000

Data Index: 217922 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.2507. Min Act: -0.0000

Data Index: 183966 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.2805. Min Act: -0.0000

Data Index: 1686854 (The Pile)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.4912. Min Act: -0.0000

Data Index: 155431 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3153. Min Range: -4.3153

Max Act: 2.3673. Min Act: -0.0000

Data Index: 307595 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #19