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

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

Neuron 931 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1374700 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1080. Min Act: -0.0001

Data Index: 385611 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1143657 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1276511 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0853. Min Act: -0.0001

Data Index: 440546 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1447216 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0882. Min Act: -0.0001

Data Index: 133289 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0770. Min Act: -0.0001

Data Index: 784456 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0788. Min Act: -0.0001

Data Index: 151497 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0767. Min Act: -0.0001

Data Index: 616699 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1152403 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0730. Min Act: -0.0001

Data Index: 541863 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0744. Min Act: -0.0001

Data Index: 459101 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1180527 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0608. Min Act: -0.0001

Data Index: 664890 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0725. Min Act: -0.0001

Data Index: 266051 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0761. Min Act: -0.0001

Data Index: 413695 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0763. Min Act: -0.0001

Data Index: 993665 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1189559 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0705. Min Act: -0.0001

Data Index: 662031 (C4 (Web Text))

Max Activating Token Index: 42