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

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

Neuron 4059 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0000

Data Index: 978880 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0689. Min Act: -0.0000

Data Index: 93354 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1654561 (Python Code)

Max Activating Token Index: 499

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1190730 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0645. Min Act: -0.0000

Data Index: 612737 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1420834 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1052684 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0577. Min Act: -0.0000

Data Index: 86275 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1265074 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1217863 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0587. Min Act: -0.0000

Data Index: 734718 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0539. Min Act: -0.0000

Data Index: 151855 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0578. Min Act: -0.0000

Data Index: 873151 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1220089 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1054387 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0594. Min Act: -0.0000

Data Index: 650893 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1343613 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0563. Min Act: -0.0000

Data Index: 162490 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0560. Min Act: -0.0000

Data Index: 730564 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1129869 (C4 (Web Text))

Max Activating Token Index: 983