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

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

Neuron 1971 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1077. Min Act: -0.0000

Data Index: 331723 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1137781 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0997. Min Act: -0.0000

Data Index: 521915 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0945. Min Act: -0.0000

Data Index: 388887 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0944. Min Act: -0.0000

Data Index: 780675 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1210148 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0895. Min Act: -0.0001

Data Index: 616717 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0865. Min Act: -0.0001

Data Index: 590212 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0872. Min Act: -0.0001

Data Index: 721420 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0836. Min Act: -0.0000

Data Index: 508643 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0862. Min Act: -0.0000

Data Index: 49426 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0865. Min Act: -0.0000

Data Index: 401869 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0837. Min Act: -0.0000

Data Index: 834541 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0823. Min Act: -0.0000

Data Index: 516762 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1060543 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0803. Min Act: -0.0000

Data Index: 17065 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0801. Min Act: -0.0001

Data Index: 624409 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0807. Min Act: -0.0000

Data Index: 904479 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0776. Min Act: -0.0000

Data Index: 406018 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1205117 (C4 (Web Text))

Max Activating Token Index: 908