Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 83 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0770. Min Act: -0.0003

Data Index: 563748 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0003

Data Index: 220417 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0720. Min Act: -0.0003

Data Index: 505733 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0706. Min Act: -0.0003

Data Index: 345381 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1039270 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0693. Min Act: -0.0003

Data Index: 596839 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0695. Min Act: -0.0003

Data Index: 894627 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0683. Min Act: -0.0003

Data Index: 881137 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0767. Min Act: -0.0003

Data Index: 715423 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1625129 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0674. Min Act: -0.0003

Data Index: 600449 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1245574 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0693. Min Act: -0.0003

Data Index: 68577 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0716. Min Act: -0.0003

Data Index: 130357 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0697. Min Act: -0.0003

Data Index: 250645 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0723. Min Act: -0.0003

Data Index: 505501 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1239462 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1198223 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0659. Min Act: -0.0003

Data Index: 611722 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0667. Min Act: -0.0003

Data Index: 475738 (C4 (Web Text))

Max Activating Token Index: 525