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

Dataset: The Pile

Neuron 3804 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: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0000

Data Index: 284163 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0696. Min Act: -0.0000

Data Index: 203277 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0693. Min Act: 0.0000

Data Index: 800508 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0689. Min Act: -0.0000

Data Index: 202598 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0651. Min Act: -0.0000

Data Index: 290484 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1655167 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0649. Min Act: 0.0000

Data Index: 1276489 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1641860 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1055769 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0628. Min Act: -0.0000

Data Index: 216190 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0625. Min Act: 0.0000

Data Index: 316618 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0619. Min Act: -0.0000

Data Index: 76355 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1017595 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0628. Min Act: 0.0001

Data Index: 904605 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0628. Min Act: -0.0000

Data Index: 285184 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0600. Min Act: 0.0001

Data Index: 1039780 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0599. Min Act: 0.0000

Data Index: 1718119 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0597. Min Act: -0.0000

Data Index: 334734 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0592. Min Act: 0.0000

Data Index: 826173 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0612. Min Act: -0.0000

Data Index: 901543 (The Pile)

Max Activating Token Index: 20