< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 8 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.7212. Min Act: -0.0001

Data Index: 1120920 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5209. Min Act: -0.0001

Data Index: 169579 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1375085 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2692. Min Act: -0.0001

Data Index: 970455 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.3111. Min Act: -0.0001

Data Index: 1156215 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2986. Min Act: -0.0001

Data Index: 1017842 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.3077. Min Act: -0.0001

Data Index: 693139 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2970. Min Act: -0.0001

Data Index: 158878 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1258745 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.3109. Min Act: -0.0001

Data Index: 708662 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1744433 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1363833 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2734. Min Act: -0.0001

Data Index: 1529657 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2671. Min Act: -0.0001

Data Index: 1311448 (The Pile)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1692131 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2677. Min Act: -0.0001

Data Index: 429772 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2829. Min Act: -0.0001

Data Index: 792725 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2552. Min Act: -0.0001

Data Index: 71550 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2971. Min Act: -0.0001

Data Index: 598505 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1796312 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #19