< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2307 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: 2.5167. Min Range: -2.5167

Max Act: 2.5167. Min Act: -0.0002

Data Index: 1739653 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.6838. Min Act: -0.0002

Data Index: 637504 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.4922. Min Act: -0.0002

Data Index: 1351700 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.4341. Min Act: -0.0002

Data Index: 1067 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.3499. Min Act: -0.0002

Data Index: 401798 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.3926. Min Act: -0.0002

Data Index: 797853 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.3785. Min Act: -0.0002

Data Index: 61094 (The Pile)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.3572. Min Act: -0.0002

Data Index: 1677601 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.2259. Min Act: -0.0002

Data Index: 845036 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.2613. Min Act: -0.0002

Data Index: 1295576 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.2127. Min Act: -0.0002

Data Index: 1241101 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1568. Min Act: -0.0002

Data Index: 1057701 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1904. Min Act: -0.0002

Data Index: 1262375 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1910. Min Act: -0.0002

Data Index: 787607 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1339. Min Act: -0.0002

Data Index: 1562099 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1730. Min Act: -0.0002

Data Index: 368317 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1505. Min Act: -0.0002

Data Index: 1164395 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.0992. Min Act: -0.0002

Data Index: 734633 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.0338. Min Act: -0.0002

Data Index: 1793897 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5167. Min Range: -2.5167

Max Act: 1.1291. Min Act: -0.0002

Data Index: 512937 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #19