< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3071 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: 2.7066. Min Range: -2.7066

Max Act: 2.7066. Min Act: -0.0001

Data Index: 1679076 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.5465. Min Act: -0.0001

Data Index: 1254127 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.4153. Min Act: -0.0001

Data Index: 373571 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.2589. Min Act: -0.0001

Data Index: 1112566 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.4425. Min Act: -0.0001

Data Index: 1019726 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.1878. Min Act: -0.0001

Data Index: 160389 (The Pile)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.3933. Min Act: -0.0001

Data Index: 1702788 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.3044. Min Act: -0.0001

Data Index: 172060 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.0888. Min Act: -0.0001

Data Index: 472221 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.1090. Min Act: -0.0001

Data Index: 678880 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.1381. Min Act: -0.0001

Data Index: 861172 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7066. Min Range: -2.7066

Max Act: 1.9790. Min Act: -0.0001

Data Index: 508103 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.1165. Min Act: -0.0001

Data Index: 661161 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.0844. Min Act: -0.0001

Data Index: 1543315 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.1069. Min Act: -0.0001

Data Index: 47907 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.1498. Min Act: -0.0001

Data Index: 1986336 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7066. Min Range: -2.7066

Max Act: 2.0135. Min Act: -0.0001

Data Index: 104866 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7066. Min Range: -2.7066

Max Act: 1.9323. Min Act: -0.0001

Data Index: 1560389 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7066. Min Range: -2.7066

Max Act: 1.9218. Min Act: -0.0001

Data Index: 98477 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7066. Min Range: -2.7066

Max Act: 1.8274. Min Act: -0.0001

Data Index: 809624 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #19