< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 33 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.6628. Min Act: -0.0004

Data Index: 1918904 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.6280. Min Act: -0.0004

Data Index: 1722145 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5485. Min Act: -0.0004

Data Index: 237359 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5750. Min Act: -0.0004

Data Index: 1512923 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5364. Min Act: -0.0004

Data Index: 1178157 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5146. Min Act: -0.0005

Data Index: 1496016 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5643. Min Act: -0.0004

Data Index: 1267419 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5247. Min Act: -0.0004

Data Index: 1230484 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5234. Min Act: -0.0004

Data Index: 833713 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5373. Min Act: -0.0004

Data Index: 889601 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5402. Min Act: -0.0004

Data Index: 27598 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5298. Min Act: -0.0004

Data Index: 1736370 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5257. Min Act: -0.0004

Data Index: 629352 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5253. Min Act: -0.0004

Data Index: 1501316 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5025. Min Act: -0.0004

Data Index: 670070 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5211. Min Act: -0.0004

Data Index: 75191 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5153. Min Act: -0.0004

Data Index: 1197409 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5098. Min Act: -0.0004

Data Index: 973229 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5249. Min Act: -0.0004

Data Index: 712791 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4903. Min Act: -0.0004

Data Index: 1932391 (The Pile)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #19