< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3029 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.1229. Min Range: -1.1229

Max Act: 1.1229. Min Act: -0.0001

Data Index: 1687597 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1229. Min Range: -1.1229

Max Act: 1.0280. Min Act: -0.0001

Data Index: 419197 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.9902. Min Act: -0.0001

Data Index: 707013 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.9906. Min Act: -0.0001

Data Index: 101179 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.9172. Min Act: -0.0001

Data Index: 1833961 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.9221. Min Act: -0.0001

Data Index: 1261049 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1168895 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1064219 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1749402 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8508. Min Act: -0.0001

Data Index: 999452 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8514. Min Act: -0.0001

Data Index: 835457 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8734. Min Act: -0.0001

Data Index: 501273 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8357. Min Act: -0.0001

Data Index: 1999629 (The Pile)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1195441 (The Pile)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8514. Min Act: -0.0001

Data Index: 23966 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8482. Min Act: -0.0001

Data Index: 823458 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8351. Min Act: -0.0001

Data Index: 767434 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.7849. Min Act: -0.0001

Data Index: 262165 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1041496 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1229. Min Range: -1.1229

Max Act: 0.7769. Min Act: -0.0001

Data Index: 979430 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #19