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

Dataset: The Pile

Neuron 55 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0594. Min Act: -0.0000

Data Index: 353200 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0000

Data Index: 379364 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0578. Min Act: 0.0000

Data Index: 256232 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0578. Min Act: 0.0000

Data Index: 1773089 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0578. Min Act: -0.0000

Data Index: 691129 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0565. Min Act: 0.0000

Data Index: 1063045 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0563. Min Act: 0.0000

Data Index: 1628213 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1873243 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0560. Min Act: -0.0000

Data Index: 43228 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0560. Min Act: -0.0000

Data Index: 942360 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0556. Min Act: 0.0000

Data Index: 1625891 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0554. Min Act: 0.0000

Data Index: 1179240 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0553. Min Act: 0.0000

Data Index: 1506900 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0553. Min Act: 0.0000

Data Index: 234412 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0552. Min Act: -0.0000

Data Index: 951756 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1266000 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0551. Min Act: 0.0000

Data Index: 1309543 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0548. Min Act: -0.0000

Data Index: 303772 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0528. Min Act: 0.0000

Data Index: 901046 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1650865 (The Pile)

Max Activating Token Index: 1023