< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5110 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: 2.5636. Min Range: -2.5636

Max Act: 2.5636. Min Act: -0.0000

Data Index: 1133648 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.3099. Min Act: -0.0000

Data Index: 144522 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.2018. Min Act: -0.0000

Data Index: 945399 (The Pile)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.1357. Min Act: -0.0000

Data Index: 747535 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1419239 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.2278. Min Act: -0.0000

Data Index: 44898 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1538197 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.0323. Min Act: -0.0000

Data Index: 72399 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.2424. Min Act: -0.0000

Data Index: 769463 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.1317. Min Act: -0.0000

Data Index: 1698877 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1337603 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.8846. Min Act: -0.0000

Data Index: 989381 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.9925. Min Act: -0.0000

Data Index: 1321483 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5636. Min Range: -2.5636

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1229400 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.8485. Min Act: -0.0000

Data Index: 347783 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1349759 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.6529. Min Act: -0.0000

Data Index: 1071808 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.9138. Min Act: -0.0000

Data Index: 966859 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.8850. Min Act: -0.0000

Data Index: 1855587 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5636. Min Range: -2.5636

Max Act: 1.8857. Min Act: -0.0000

Data Index: 180365 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #19