Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5306 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0001

Data Index: 244398 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1057. Min Act: -0.0001

Data Index: 679588 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1467620 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0936. Min Act: -0.0001

Data Index: 856782 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0891. Min Act: -0.0001

Data Index: 915320 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0842. Min Act: -0.0001

Data Index: 493232 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1479701 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1445390 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0781. Min Act: -0.0001

Data Index: 749104 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1112368 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1440953 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0838. Min Act: -0.0001

Data Index: 667147 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0982. Min Act: -0.0001

Data Index: 329560 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1393179 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0681. Min Act: -0.0001

Data Index: 150999 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1283557 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1211959 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0771. Min Act: -0.0001

Data Index: 659203 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0769. Min Act: -0.0001

Data Index: 745844 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0770. Min Act: -0.0001

Data Index: 918064 (C4 (Web Text))

Max Activating Token Index: 146