< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 48 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.1056. Min Range: -2.1056

Max Act: 2.1056. Min Act: -0.0000

Data Index: 1662074 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.7509. Min Act: -0.0000

Data Index: 1127038 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.3248. Min Act: -0.0000

Data Index: 1721854 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1457362 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.3388. Min Act: -0.0000

Data Index: 244187 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.3974. Min Act: -0.0000

Data Index: 273443 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1164714 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1956055 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1881373 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1711187 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.2337. Min Act: -0.0000

Data Index: 876174 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1508. Min Act: -0.0000

Data Index: 602313 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1463. Min Act: -0.0000

Data Index: 754400 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1242. Min Act: -0.0000

Data Index: 328676 (The Pile)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1073925 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1643219 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1779515 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1905305 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1889288 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1056. Min Range: -2.1056

Max Act: 1.1197. Min Act: -0.0000

Data Index: 788241 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #19