< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3024 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: 3.2751. Min Range: -3.2751

Max Act: 3.2751. Min Act: -0.0001

Data Index: 707496 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2751. Min Range: -3.2751

Max Act: 3.1744. Min Act: -0.0001

Data Index: 1187405 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.5845. Min Act: -0.0001

Data Index: 189621 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.4608. Min Act: -0.0001

Data Index: 819665 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.6194. Min Act: -0.0001

Data Index: 779144 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.5530. Min Act: -0.0001

Data Index: 542200 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.2928. Min Act: -0.0001

Data Index: 1750160 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.6447. Min Act: -0.0001

Data Index: 330907 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.4906. Min Act: -0.0001

Data Index: 1198529 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.4531. Min Act: -0.0001

Data Index: 1516366 (The Pile)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.5553. Min Act: -0.0001

Data Index: 1713087 (The Pile)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.2964. Min Act: -0.0001

Data Index: 871777 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.3875. Min Act: -0.0001

Data Index: 195331 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.2587. Min Act: -0.0001

Data Index: 166057 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.3491. Min Act: -0.0001

Data Index: 512083 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.1048. Min Act: -0.0001

Data Index: 550238 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.2005. Min Act: -0.0001

Data Index: 481058 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.5467. Min Act: -0.0001

Data Index: 1094564 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.2924. Min Act: -0.0001

Data Index: 1356894 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2751. Min Range: -3.2751

Max Act: 2.2795. Min Act: -0.0001

Data Index: 1908309 (The Pile)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #19