< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 12 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: 1.5255. Min Range: -1.5255

Max Act: 1.5255. Min Act: -0.0000

Data Index: 826936 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.5232. Min Act: -0.0001

Data Index: 623365 (The Pile)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2343. Min Act: -0.0001

Data Index: 937818 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2004. Min Act: -0.0001

Data Index: 1421533 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.0935. Min Act: -0.0001

Data Index: 1089880 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1075750 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.1354. Min Act: -0.0001

Data Index: 54507 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.0450. Min Act: -0.0001

Data Index: 600719 (The Pile)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9926. Min Act: -0.0001

Data Index: 308479 (The Pile)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9764. Min Act: -0.0001

Data Index: 844718 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9722. Min Act: -0.0001

Data Index: 581013 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9869. Min Act: -0.0001

Data Index: 172394 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.0715. Min Act: -0.0001

Data Index: 602808 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9814. Min Act: -0.0001

Data Index: 1243368 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9339. Min Act: -0.0001

Data Index: 1470130 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9678. Min Act: -0.0001

Data Index: 196180 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.0262. Min Act: -0.0001

Data Index: 1743515 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.0101. Min Act: -0.0001

Data Index: 133450 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.9886. Min Act: -0.0001

Data Index: 452816 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5255. Min Range: -1.5255

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1835798 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #19