Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1992 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1002544 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0711. Min Act: -0.0002

Data Index: 244380 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0693. Min Act: -0.0001

Data Index: 721425 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1090538 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0671. Min Act: -0.0002

Data Index: 389685 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0683. Min Act: -0.0002

Data Index: 498048 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0663. Min Act: -0.0002

Data Index: 447524 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0671. Min Act: -0.0002

Data Index: 389202 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0658. Min Act: -0.0002

Data Index: 365881 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1103530 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0674. Min Act: -0.0002

Data Index: 233532 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0658. Min Act: -0.0001

Data Index: 23539 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1295393 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0653. Min Act: -0.0002

Data Index: 553844 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0660. Min Act: -0.0002

Data Index: 471604 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0653. Min Act: -0.0002

Data Index: 554720 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1349863 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0660. Min Act: -0.0002

Data Index: 841361 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0647. Min Act: -0.0002

Data Index: 639846 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0648. Min Act: -0.0002

Data Index: 302727 (C4 (Web Text))

Max Activating Token Index: 563