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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4410 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0001

Data Index: 859915 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1553541 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0858. Min Act: -0.0001

Data Index: 882700 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1583441 (Python Code)

Max Activating Token Index: 695

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0920. Min Act: -0.0001

Data Index: 309304 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1418855 (Python Code)

Max Activating Token Index: 422

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0892. Min Act: -0.0001

Data Index: 634044 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1568100 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1514168 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1160044 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0893. Min Act: -0.0001

Data Index: 35675 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0858. Min Act: -0.0001

Data Index: 497773 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0862. Min Act: -0.0001

Data Index: 954564 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0852. Min Act: -0.0001

Data Index: 749465 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1384712 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1463132 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0852. Min Act: -0.0001

Data Index: 491525 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1086839 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0823. Min Act: -0.0001

Data Index: 53157 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1394623 (Python Code)

Max Activating Token Index: 65