< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 39 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: 0.2050. Min Range: -0.2050

Max Act: 0.2050. Min Act: -0.0000

Data Index: 397566 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1110531 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1888794 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1290. Min Act: -0.0000

Data Index: 110187 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1270. Min Act: -0.0000

Data Index: 355747 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1095639 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1065. Min Act: -0.0000

Data Index: 6736 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1374189 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0907. Min Act: -0.0000

Data Index: 186379 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1609412 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1015. Min Act: -0.0000

Data Index: 995954 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1890704 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0911. Min Act: -0.0000

Data Index: 542110 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0839. Min Act: -0.0000

Data Index: 360261 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1022. Min Act: -0.0000

Data Index: 830549 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1289508 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1849780 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1274817 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1555429 (The Pile)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1206132 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #19