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

Dataset: The Pile

Neuron 3639 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: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1187260 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0852. Min Act: -0.0000

Data Index: 493800 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0728. Min Act: -0.0000

Data Index: 359980 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0707. Min Act: -0.0000

Data Index: 653355 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1411577 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0697. Min Act: -0.0000

Data Index: 307973 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0641. Min Act: -0.0000

Data Index: 273877 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0608. Min Act: 0.0000

Data Index: 432704 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0628. Min Act: -0.0000

Data Index: 216432 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0628. Min Act: 0.0000

Data Index: 1185264 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0627. Min Act: -0.0000

Data Index: 101479 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1121242 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0621. Min Act: 0.0000

Data Index: 525715 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1564500 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1871461 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1276218 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0608. Min Act: -0.0000

Data Index: 774136 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1023825 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1297660 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0596. Min Act: 0.0000

Data Index: 637620 (The Pile)

Max Activating Token Index: 309