< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4093 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.6386. Min Act: -0.0001

Data Index: 1138795 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.5719. Min Act: -0.0001

Data Index: 691692 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.4164. Min Act: -0.0001

Data Index: 1614457 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.4251. Min Act: -0.0001

Data Index: 1118986 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.3001. Min Act: -0.0001

Data Index: 1437948 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.4141. Min Act: -0.0001

Data Index: 1527027 (The Pile)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2735. Min Act: -0.0001

Data Index: 922485 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2344. Min Act: -0.0001

Data Index: 306539 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.3404. Min Act: -0.0001

Data Index: 1257117 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2807. Min Act: -0.0001

Data Index: 1352614 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2631. Min Act: -0.0001

Data Index: 569649 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.3225. Min Act: -0.0001

Data Index: 1006674 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2873. Min Act: -0.0001

Data Index: 1230706 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2245. Min Act: -0.0001

Data Index: 1567271 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.3483. Min Act: -0.0001

Data Index: 1020047 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2922. Min Act: -0.0001

Data Index: 236277 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2886. Min Act: -0.0001

Data Index: 221460 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.1715. Min Act: -0.0001

Data Index: 1689883 (The Pile)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.3399. Min Act: -0.0001

Data Index: 1980216 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6386. Min Range: -1.6386

Max Act: 1.2998. Min Act: -0.0001

Data Index: 767731 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #19