< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 10 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.6876. Min Act: -0.0001

Data Index: 738426 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.7080. Min Act: -0.0001

Data Index: 1526339 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.6302. Min Act: -0.0001

Data Index: 561784 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.6407. Min Act: -0.0001

Data Index: 621362 (The Pile)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.5597. Min Act: -0.0001

Data Index: 1619289 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.6236. Min Act: -0.0001

Data Index: 1057233 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.4822. Min Act: -0.0001

Data Index: 398374 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3217. Min Act: -0.0001

Data Index: 270168 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3919. Min Act: -0.0001

Data Index: 1256293 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3260. Min Act: -0.0001

Data Index: 402414 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.4647. Min Act: -0.0002

Data Index: 1590053 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3796. Min Act: -0.0001

Data Index: 345110 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.5882. Min Act: -0.0001

Data Index: 1611724 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3210. Min Act: -0.0001

Data Index: 509861 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2354. Min Act: -0.0001

Data Index: 285177 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3927. Min Act: -0.0001

Data Index: 768843 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3427. Min Act: -0.0001

Data Index: 1964060 (The Pile)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2625. Min Act: -0.0001

Data Index: 1151197 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3886. Min Act: -0.0001

Data Index: 37080 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3321. Min Act: -0.0001

Data Index: 737135 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #19