< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 22 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.8465. Min Act: -0.0001

Data Index: 1757039 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7252. Min Act: -0.0001

Data Index: 1397560 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7860. Min Act: -0.0001

Data Index: 1760114 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.4179. Min Act: -0.0001

Data Index: 1174627 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.6015. Min Act: -0.0001

Data Index: 1433237 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.1707. Min Act: -0.0001

Data Index: 1187715 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.0066. Min Act: -0.0001

Data Index: 1456290 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.9685. Min Act: -0.0001

Data Index: 512711 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.8397. Min Act: -0.0001

Data Index: 1460084 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.8397. Min Act: -0.0001

Data Index: 1021749 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.6954. Min Act: -0.0001

Data Index: 1318155 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.6272. Min Act: -0.0001

Data Index: 1721266 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.1150. Min Act: -0.0001

Data Index: 1098332 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.8292. Min Act: -0.0001

Data Index: 188731 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.2114. Min Act: -0.0001

Data Index: 1201963 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.6862. Min Act: -0.0001

Data Index: 488312 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.6745. Min Act: -0.0001

Data Index: 1164492 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.7117. Min Act: -0.0001

Data Index: 498160 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.6043. Min Act: -0.0001

Data Index: 1128929 (The Pile)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8465. Min Range: -3.8465

Max Act: 2.6542. Min Act: -0.0001

Data Index: 1060773 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #19