< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.9343. Min Act: -0.0000

Data Index: 143572 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.6200. Min Act: -0.0000

Data Index: 382915 (The Pile)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.5877. Min Act: -0.0000

Data Index: 967835 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.5940. Min Act: -0.0000

Data Index: 1294380 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.4288. Min Act: -0.0000

Data Index: 1070198 (The Pile)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.5252. Min Act: -0.0000

Data Index: 458397 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.4873. Min Act: -0.0000

Data Index: 507033 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.4672. Min Act: -0.0000

Data Index: 716537 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.4566. Min Act: -0.0000

Data Index: 571860 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.4303. Min Act: -0.0000

Data Index: 224823 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1083124 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.3876. Min Act: -0.0000

Data Index: 1114226 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.3608. Min Act: -0.0000

Data Index: 802846 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.2405. Min Act: -0.0000

Data Index: 536297 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1376115 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.2855. Min Act: -0.0000

Data Index: 699268 (The Pile)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.2775. Min Act: -0.0000

Data Index: 1351928 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.2680. Min Act: -0.0000

Data Index: 1175660 (The Pile)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.1420. Min Act: -0.0000

Data Index: 929568 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9343. Min Range: -2.9343

Max Act: 2.2324. Min Act: -0.0000

Data Index: 1134098 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #19