Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3517 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0001

Data Index: 685408 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1299009 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1275902 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0676. Min Act: -0.0001

Data Index: 772919 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0649. Min Act: -0.0001

Data Index: 956753 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0725. Min Act: -0.0001

Data Index: 459058 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0695. Min Act: -0.0001

Data Index: 199343 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0684. Min Act: -0.0001

Data Index: 168774 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1030788 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1236936 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1081696 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0642. Min Act: -0.0001

Data Index: 250425 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1101991 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0618. Min Act: -0.0001

Data Index: 982401 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0600. Min Act: -0.0001

Data Index: 816720 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1170427 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1010796 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0608. Min Act: -0.0001

Data Index: 776229 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0612. Min Act: -0.0000

Data Index: 925040 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1061708 (C4 (Web Text))

Max Activating Token Index: 143