< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1756260 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7075. Min Act: -0.0000

Data Index: 399491 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1884209 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6794. Min Act: -0.0000

Data Index: 350158 (The Pile)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7051. Min Act: -0.0000

Data Index: 387259 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6937. Min Act: -0.0000

Data Index: 290599 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1233797 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1119884 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6050. Min Act: -0.0000

Data Index: 484241 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6059. Min Act: -0.0000

Data Index: 742166 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6145. Min Act: -0.0000

Data Index: 329567 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5946. Min Act: -0.0000

Data Index: 610222 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5722. Min Act: -0.0000

Data Index: 676157 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1049098 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1009498 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1930510 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1361084 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1033235 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1548074 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1562993 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #19