< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 54 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: 1.6083. Min Range: -1.6083

Max Act: 1.6083. Min Act: -0.0001

Data Index: 1990425 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3398. Min Act: -0.0001

Data Index: 1369787 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3788. Min Act: -0.0001

Data Index: 545843 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3356. Min Act: -0.0001

Data Index: 1624914 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.0038. Min Act: -0.0001

Data Index: 1620758 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.4013. Min Act: -0.0001

Data Index: 510895 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2380. Min Act: -0.0001

Data Index: 1397744 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1408. Min Act: -0.0001

Data Index: 1636991 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1593948 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3384. Min Act: -0.0001

Data Index: 547249 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2502. Min Act: -0.0001

Data Index: 1200394 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3056. Min Act: -0.0001

Data Index: 1109081 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1572. Min Act: -0.0001

Data Index: 1851707 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1553. Min Act: -0.0001

Data Index: 1665291 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1145450 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1799. Min Act: -0.0001

Data Index: 1955218 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2420. Min Act: -0.0001

Data Index: 1248135 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1263. Min Act: -0.0001

Data Index: 1280165 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2555. Min Act: -0.0001

Data Index: 769319 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2126. Min Act: -0.0001

Data Index: 24080 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #19