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

Dataset: The Pile

Neuron 3754 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: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1594274 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0685. Min Act: -0.0000

Data Index: 742643 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0649. Min Act: -0.0000

Data Index: 578594 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0669. Min Act: -0.0000

Data Index: 302660 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0666. Min Act: -0.0000

Data Index: 988887 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0660. Min Act: -0.0000

Data Index: 778664 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0659. Min Act: -0.0000

Data Index: 45001 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1232006 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0650. Min Act: -0.0000

Data Index: 711477 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0648. Min Act: -0.0000

Data Index: 518094 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0647. Min Act: -0.0000

Data Index: 718320 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1944946 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1094490 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1124296 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1188941 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1820288 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1777394 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0641. Min Act: -0.0000

Data Index: 224848 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1171247 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1369585 (The Pile)

Max Activating Token Index: 1023