< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 41 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.8994. Min Act: -0.0000

Data Index: 520166 (The Pile)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1481312 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.7760. Min Act: -0.0000

Data Index: 462891 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1420417 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4660. Min Act: -0.0000

Data Index: 457399 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1042427 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4611. Min Act: -0.0000

Data Index: 103438 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4663. Min Act: -0.0000

Data Index: 745577 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1260965 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.5165. Min Act: -0.0000

Data Index: 478869 (The Pile)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4070. Min Act: -0.0000

Data Index: 658147 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.3951. Min Act: -0.0000

Data Index: 659894 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1787415 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.3865. Min Act: -0.0000

Data Index: 206907 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4171. Min Act: -0.0000

Data Index: 854708 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.3211. Min Act: -0.0000

Data Index: 4863 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1467676 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1983581 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1464898 (The Pile)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.8994. Min Range: -1.8994

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1524739 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #19