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

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

Neuron 2898 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: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1580980 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0756. Min Act: -0.0002

Data Index: 932767 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0747. Min Act: -0.0002

Data Index: 499299 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1331866 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0718. Min Act: -0.0002

Data Index: 379271 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0733. Min Act: -0.0002

Data Index: 572734 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0694. Min Act: -0.0002

Data Index: 209422 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1549414 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1252981 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1421321 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0680. Min Act: -0.0002

Data Index: 831587 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1523213 (Python Code)

Max Activating Token Index: 517

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0676. Min Act: -0.0002

Data Index: 492983 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0681. Min Act: -0.0002

Data Index: 793623 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0670. Min Act: -0.0002

Data Index: 291532 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1593665 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0658. Min Act: -0.0002

Data Index: 719168 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0694. Min Act: -0.0002

Data Index: 791388 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1559722 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0669. Min Act: -0.0002

Data Index: 944980 (C4 (Web Text))

Max Activating Token Index: 304