< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1144028 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1172526 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.3945. Min Act: -0.0000

Data Index: 856185 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.3980. Min Act: -0.0000

Data Index: 787104 (The Pile)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.2485. Min Act: -0.0000

Data Index: 304577 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.2229. Min Act: -0.0000

Data Index: 931840 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1516. Min Act: -0.0000

Data Index: 581755 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1158875 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.2540. Min Act: -0.0000

Data Index: 361947 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1199196 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1982. Min Act: -0.0000

Data Index: 491366 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1788042 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9904. Min Act: -0.0000

Data Index: 264685 (The Pile)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1941270 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1799929 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1591194 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1692824 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1578889 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.0925. Min Act: -0.0000

Data Index: 575366 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1798849 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #19