< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2329 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: 1.5801. Min Range: -1.5801

Max Act: 1.5801. Min Act: -0.0001

Data Index: 1588882 (The Pile)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.4464. Min Act: -0.0001

Data Index: 1047155 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.4105. Min Act: -0.0001

Data Index: 575118 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.4015. Min Act: -0.0001

Data Index: 173848 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.3194. Min Act: -0.0001

Data Index: 817618 (The Pile)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.3170. Min Act: -0.0001

Data Index: 1384697 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.3740. Min Act: -0.0001

Data Index: 1360021 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.2621. Min Act: -0.0001

Data Index: 692840 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.2680. Min Act: -0.0001

Data Index: 2553 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.1938. Min Act: -0.0001

Data Index: 575468 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.2276. Min Act: -0.0001

Data Index: 1077476 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.2526. Min Act: -0.0001

Data Index: 915535 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.2218. Min Act: -0.0001

Data Index: 35208 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1967714 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.1608. Min Act: -0.0001

Data Index: 1215847 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.1947. Min Act: -0.0001

Data Index: 392113 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.1616. Min Act: -0.0001

Data Index: 1916994 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.1293. Min Act: -0.0001

Data Index: 1055978 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0995. Min Act: -0.0001

Data Index: 1390609 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0695. Min Act: -0.0001

Data Index: 284369 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #19