< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 7 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1639472 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1515079 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1819322 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2213. Min Act: -0.0000

Data Index: 610885 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2250. Min Act: -0.0000

Data Index: 1431067 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1528. Min Act: -0.0000

Data Index: 14027 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1644983 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2568. Min Act: -0.0000

Data Index: 679935 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1218635 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1994774 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1755. Min Act: -0.0000

Data Index: 220874 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1825. Min Act: -0.0000

Data Index: 10066 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1683882 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1295241 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1807822 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1212693 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1690760 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1556372 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1497586 (The Pile)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1705040 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #19