< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 51 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.5573. Min Act: -0.0000

Data Index: 619431 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.5235. Min Act: -0.0000

Data Index: 1863992 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.3732. Min Act: -0.0000

Data Index: 193426 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.3688. Min Act: -0.0000

Data Index: 995693 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.2992. Min Act: -0.0000

Data Index: 956714 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.3288. Min Act: -0.0000

Data Index: 1146254 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.2386. Min Act: -0.0000

Data Index: 73459 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.1457. Min Act: -0.0000

Data Index: 528297 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.2744. Min Act: -0.0000

Data Index: 1449154 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.1093. Min Act: -0.0000

Data Index: 1800102 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.8917. Min Act: -0.0000

Data Index: 1873370 (The Pile)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.8336. Min Act: -0.0000

Data Index: 1236818 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.1406. Min Act: -0.0000

Data Index: 519798 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.5573. Min Range: -4.5573

Max Act: 4.0786. Min Act: -0.0000

Data Index: 869547 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.7404. Min Act: -0.0000

Data Index: 513709 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.8717. Min Act: -0.0000

Data Index: 764111 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.7311. Min Act: -0.0000

Data Index: 1614828 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.8542. Min Act: -0.0000

Data Index: 1209831 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.9905. Min Act: -0.0000

Data Index: 1616785 (The Pile)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.5573. Min Range: -4.5573

Max Act: 3.7986. Min Act: -0.0000

Data Index: 988365 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #19