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

Dataset: The Pile

Neuron 3399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1271088 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.8021. Min Act: -0.0000

Data Index: 984912 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1789585 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1538706 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7826. Min Act: -0.0000

Data Index: 382130 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7649. Min Act: -0.0000

Data Index: 123653 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1197235 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6986. Min Act: -0.0000

Data Index: 160524 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1869991 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1934303 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1370783 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7620. Min Act: -0.0000

Data Index: 64401 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1469287 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1871549 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1929148 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6556. Min Act: -0.0000

Data Index: 746535 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1945054 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1610891 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6681. Min Act: -0.0000

Data Index: 820608 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6665. Min Act: -0.0000

Data Index: 688341 (The Pile)

Max Activating Token Index: 994