< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.4379. Min Act: -0.0002

Data Index: 1448728 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.4597. Min Act: -0.0002

Data Index: 1961981 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.4161. Min Act: -0.0002

Data Index: 822138 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.3849. Min Act: -0.0002

Data Index: 467878 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.3241. Min Act: -0.0002

Data Index: 1921 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2797. Min Act: -0.0002

Data Index: 1907882 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2812. Min Act: -0.0002

Data Index: 656458 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2821. Min Act: -0.0002

Data Index: 1261186 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2342. Min Act: -0.0002

Data Index: 964156 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2691. Min Act: -0.0002

Data Index: 1038227 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2701. Min Act: -0.0002

Data Index: 1646786 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2475. Min Act: -0.0002

Data Index: 1556905 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2050. Min Act: -0.0002

Data Index: 206891 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.1720. Min Act: -0.0002

Data Index: 860274 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2328. Min Act: -0.0002

Data Index: 698328 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.1318. Min Act: -0.0002

Data Index: 474528 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2223. Min Act: -0.0002

Data Index: 1203973 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.1710. Min Act: -0.0002

Data Index: 1719979 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2065. Min Act: -0.0002

Data Index: 1101393 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.1076. Min Act: -0.0002

Data Index: 1977315 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #19