< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1108728 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0383. Min Act: -0.0002

Data Index: 994268 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1532599 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0343. Min Act: -0.0002

Data Index: 17376 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0345. Min Act: -0.0002

Data Index: 482265 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0323. Min Act: -0.0002

Data Index: 827238 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0307. Min Act: -0.0002

Data Index: 537593 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0312. Min Act: -0.0002

Data Index: 97406 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0306. Min Act: -0.0002

Data Index: 874957 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1533577 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0290. Min Act: -0.0002

Data Index: 169874 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1599400 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0290. Min Act: -0.0002

Data Index: 509502 (The Pile)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0286. Min Act: -0.0002

Data Index: 251655 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0281. Min Act: -0.0002

Data Index: 648325 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1179193 (The Pile)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0292. Min Act: -0.0002

Data Index: 732787 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0280. Min Act: -0.0002

Data Index: 291759 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1994847 (The Pile)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0274. Min Act: -0.0002

Data Index: 221416 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #19