< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 22 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1024400 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1270672 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5478. Min Act: -0.0001

Data Index: 1491635 (The Pile)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5112. Min Act: -0.0001

Data Index: 43273 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1448124 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4822. Min Act: -0.0001

Data Index: 28149 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5021. Min Act: -0.0001

Data Index: 307338 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4608. Min Act: -0.0001

Data Index: 72970 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1870142 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4853. Min Act: -0.0001

Data Index: 22567 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4376. Min Act: -0.0001

Data Index: 1669500 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4189. Min Act: -0.0001

Data Index: 757205 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.3956. Min Act: -0.0001

Data Index: 318241 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.3859. Min Act: -0.0001

Data Index: 949324 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4106. Min Act: -0.0001

Data Index: 382980 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.3748. Min Act: -0.0001

Data Index: 287385 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1342306 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.3851. Min Act: -0.0001

Data Index: 761617 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1444793 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1250123 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #19