< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 25 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.2487. Min Range: -2.2487

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1774145 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.9516. Min Act: -0.0000

Data Index: 184177 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2487. Min Range: -2.2487

Max Act: 2.0343. Min Act: -0.0000

Data Index: 161948 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2487. Min Range: -2.2487

Max Act: 2.0732. Min Act: -0.0000

Data Index: 221793 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.8265. Min Act: -0.0000

Data Index: 87232 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.8155. Min Act: -0.0000

Data Index: 1535650 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.8817. Min Act: -0.0000

Data Index: 1694422 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.8952. Min Act: -0.0000

Data Index: 1601628 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.8327. Min Act: -0.0000

Data Index: 929134 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7267. Min Act: -0.0000

Data Index: 848765 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1612157 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7540. Min Act: -0.0000

Data Index: 1604098 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7788. Min Act: -0.0000

Data Index: 572043 (The Pile)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7649. Min Act: -0.0000

Data Index: 844911 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7554. Min Act: -0.0000

Data Index: 1391367 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1690619 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.6932. Min Act: -0.0000

Data Index: 295097 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1664519 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7490. Min Act: -0.0000

Data Index: 886866 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2487. Min Range: -2.2487

Max Act: 1.7014. Min Act: -0.0000

Data Index: 392809 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #19