< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8528. Min Act: -0.0002

Data Index: 1490699 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8366. Min Act: -0.0002

Data Index: 1524203 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8059. Min Act: -0.0002

Data Index: 995877 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8160. Min Act: -0.0002

Data Index: 1804872 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6704. Min Act: -0.0002

Data Index: 1951081 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6750. Min Act: -0.0002

Data Index: 247004 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6162. Min Act: -0.0002

Data Index: 1198090 (The Pile)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5885. Min Act: -0.0002

Data Index: 249349 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6660. Min Act: -0.0002

Data Index: 1442344 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6284. Min Act: -0.0002

Data Index: 146779 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.7339. Min Act: -0.0002

Data Index: 1582728 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5903. Min Act: -0.0002

Data Index: 918966 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5264. Min Act: -0.0002

Data Index: 797465 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5026. Min Act: -0.0002

Data Index: 87828 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5175. Min Act: -0.0002

Data Index: 467178 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5266. Min Act: -0.0002

Data Index: 1521685 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5200. Min Act: -0.0002

Data Index: 843913 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5291. Min Act: -0.0002

Data Index: 530777 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5614. Min Act: -0.0002

Data Index: 1059762 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5237. Min Act: -0.0002

Data Index: 213826 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #19