< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4048 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2446. Min Act: -0.0001

Data Index: 485906 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2368. Min Act: -0.0001

Data Index: 470738 (The Pile)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2374. Min Act: -0.0001

Data Index: 860481 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1009710 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2354. Min Act: -0.0001

Data Index: 510715 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1370559 (The Pile)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1811288 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2141. Min Act: -0.0001

Data Index: 1033930 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2251. Min Act: -0.0001

Data Index: 243915 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2576. Min Act: -0.0001

Data Index: 1455958 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2144. Min Act: -0.0000

Data Index: 77818 (The Pile)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2282. Min Act: -0.0001

Data Index: 147761 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2521. Min Act: -0.0001

Data Index: 279054 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2275. Min Act: -0.0001

Data Index: 552035 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1699279 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1406860 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1707167 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1915. Min Act: -0.0001

Data Index: 775836 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2787. Min Act: -0.0000

Data Index: 265054 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1068370 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #19