< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 67 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.6557. Min Range: -2.6557

Max Act: 2.6557. Min Act: -0.0001

Data Index: 631413 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6557. Min Range: -2.6557

Max Act: 2.1415. Min Act: -0.0001

Data Index: 973412 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6557. Min Range: -2.6557

Max Act: 2.1193. Min Act: -0.0001

Data Index: 1762506 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6557. Min Range: -2.6557

Max Act: 2.1496. Min Act: -0.0001

Data Index: 100442 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8829. Min Act: -0.0001

Data Index: 1591477 (The Pile)

Max Activating Token Index: 953

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.7797. Min Act: -0.0001

Data Index: 476690 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.7911. Min Act: -0.0001

Data Index: 1101843 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8501. Min Act: -0.0001

Data Index: 790041 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8115. Min Act: -0.0001

Data Index: 2248 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8043. Min Act: -0.0001

Data Index: 608866 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.9031. Min Act: -0.0001

Data Index: 797853 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6557. Min Range: -2.6557

Max Act: 2.0893. Min Act: -0.0001

Data Index: 49299 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8862. Min Act: -0.0001

Data Index: 1843996 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.9475. Min Act: -0.0001

Data Index: 486445 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8495. Min Act: -0.0001

Data Index: 1975383 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.7542. Min Act: -0.0001

Data Index: 1042310 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.9696. Min Act: -0.0001

Data Index: 725661 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.7466. Min Act: -0.0001

Data Index: 1154801 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8485. Min Act: -0.0001

Data Index: 1474503 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6557. Min Range: -2.6557

Max Act: 1.8214. Min Act: -0.0001

Data Index: 1126546 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #19