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

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

Neuron 4050 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.9102. Min Act: -0.0002

Data Index: 1606595 (Python Code)

Max Activating Token Index: 809

Text #1

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8907. Min Act: -0.0002

Data Index: 42911 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8434. Min Act: -0.0002

Data Index: 1592621 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7989. Min Act: -0.0002

Data Index: 1456423 (Python Code)

Max Activating Token Index: 977

Text #4

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7969. Min Act: -0.0002

Data Index: 687482 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7829. Min Act: -0.0002

Data Index: 1628708 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7856. Min Act: -0.0002

Data Index: 1545862 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7832. Min Act: -0.0002

Data Index: 1559724 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7790. Min Act: -0.0002

Data Index: 1624254 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7903. Min Act: -0.0002

Data Index: 1497666 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7677. Min Act: -0.0002

Data Index: 975273 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7574. Min Act: -0.0002

Data Index: 1441216 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7744. Min Act: -0.0002

Data Index: 1620521 (Python Code)

Max Activating Token Index: 791

Text #13

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7671. Min Act: -0.0002

Data Index: 1196140 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7745. Min Act: -0.0002

Data Index: 818326 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7666. Min Act: -0.0002

Data Index: 1389021 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7746. Min Act: -0.0002

Data Index: 35788 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7561. Min Act: -0.0002

Data Index: 1472515 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7662. Min Act: -0.0002

Data Index: 1387826 (Python Code)

Max Activating Token Index: 447

Text #19

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7675. Min Act: -0.0002

Data Index: 1411743 (Python Code)

Max Activating Token Index: 88