< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 17 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7571. Min Act: -0.0001

Data Index: 606508 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1995351 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7411. Min Act: -0.0001

Data Index: 126540 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7299. Min Act: -0.0001

Data Index: 754334 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7219. Min Act: -0.0001

Data Index: 1633054 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6961. Min Act: -0.0001

Data Index: 1975836 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7073. Min Act: -0.0001

Data Index: 1136079 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6833. Min Act: -0.0001

Data Index: 208429 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1819751 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6944. Min Act: -0.0001

Data Index: 1857425 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6934. Min Act: -0.0001

Data Index: 930693 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6896. Min Act: -0.0001

Data Index: 947280 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1596021 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6860. Min Act: -0.0001

Data Index: 1348749 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6814. Min Act: -0.0001

Data Index: 1198440 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6777. Min Act: -0.0001

Data Index: 858362 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6739. Min Act: -0.0001

Data Index: 1448419 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6632. Min Act: -0.0001

Data Index: 368391 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6642. Min Act: -0.0001

Data Index: 1772607 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6608. Min Act: -0.0001

Data Index: 728282 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #19