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

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

Neuron 2624 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1230925 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1535040 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0950. Min Act: -0.0000

Data Index: 321500 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1000001 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0797. Min Act: -0.0000

Data Index: 341100 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1374871 (Python Code)

Max Activating Token Index: 249

Text #6

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0790. Min Act: -0.0000

Data Index: 246888 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1428039 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0831. Min Act: -0.0000

Data Index: 326970 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1379682 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1504963 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0741. Min Act: -0.0000

Data Index: 332411 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0756. Min Act: -0.0000

Data Index: 923114 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0735. Min Act: -0.0000

Data Index: 196765 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1476170 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0707. Min Act: -0.0000

Data Index: 138153 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1533094 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0668. Min Act: -0.0000

Data Index: 918595 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0661. Min Act: -0.0000

Data Index: 227260 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0638. Min Act: -0.0000

Data Index: 548276 (C4 (Web Text))

Max Activating Token Index: 427