< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 7 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.6806. Min Act: -0.0001

Data Index: 1353543 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.5054. Min Act: -0.0001

Data Index: 820433 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.3511. Min Act: -0.0001

Data Index: 402851 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.3468. Min Act: -0.0001

Data Index: 1034859 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.2235. Min Act: -0.0001

Data Index: 427302 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.4134. Min Act: -0.0001

Data Index: 1342883 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.4252. Min Act: -0.0001

Data Index: 410346 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.3056. Min Act: -0.0001

Data Index: 1470388 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.2580. Min Act: -0.0001

Data Index: 1080461 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.2780. Min Act: -0.0001

Data Index: 447772 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.1872. Min Act: -0.0001

Data Index: 654911 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.2482. Min Act: -0.0001

Data Index: 884446 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.1424. Min Act: -0.0001

Data Index: 931750 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.0339. Min Act: -0.0001

Data Index: 1639262 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.1205. Min Act: -0.0001

Data Index: 697467 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6806. Min Range: -2.6806

Max Act: 1.8808. Min Act: -0.0001

Data Index: 600451 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.0672. Min Act: -0.0001

Data Index: 1588446 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6806. Min Range: -2.6806

Max Act: 1.9710. Min Act: -0.0001

Data Index: 323754 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.0551. Min Act: -0.0001

Data Index: 923001 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6806. Min Range: -2.6806

Max Act: 2.0462. Min Act: -0.0001

Data Index: 965450 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #19