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

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

Neuron 5934 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0001

Data Index: 952993 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1028387 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0688. Min Act: -0.0001

Data Index: 961210 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0706. Min Act: -0.0001

Data Index: 987350 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0693. Min Act: -0.0001

Data Index: 127855 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1001535 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0686. Min Act: -0.0001

Data Index: 598703 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1004548 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0657. Min Act: -0.0001

Data Index: 574336 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1180819 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0635. Min Act: -0.0001

Data Index: 61278 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0668. Min Act: -0.0001

Data Index: 829801 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0621. Min Act: -0.0001

Data Index: 385444 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0603. Min Act: -0.0001

Data Index: 91238 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0615. Min Act: -0.0001

Data Index: 531174 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0608. Min Act: -0.0001

Data Index: 153036 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0590. Min Act: -0.0001

Data Index: 498436 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1129586 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1220671 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0582. Min Act: -0.0001

Data Index: 539809 (C4 (Web Text))

Max Activating Token Index: 639