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

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

Neuron 4434 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: 0.6636. Min Range: -0.6636

Max Act: 0.6636. Min Act: -0.0002

Data Index: 276886 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6555. Min Act: -0.0002

Data Index: 879718 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6540. Min Act: -0.0002

Data Index: 851704 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6461. Min Act: -0.0002

Data Index: 468097 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6447. Min Act: -0.0002

Data Index: 596154 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6267. Min Act: -0.0002

Data Index: 738184 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6331. Min Act: -0.0002

Data Index: 602684 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5953. Min Act: -0.0002

Data Index: 1131083 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5918. Min Act: -0.0002

Data Index: 154743 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5895. Min Act: -0.0002

Data Index: 1041641 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5685. Min Act: -0.0002

Data Index: 185197 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5640. Min Act: -0.0002

Data Index: 865449 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5665. Min Act: -0.0002

Data Index: 745262 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5559. Min Act: -0.0002

Data Index: 1035238 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5633. Min Act: -0.0002

Data Index: 93110 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5642. Min Act: -0.0002

Data Index: 838239 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5636. Min Act: -0.0002

Data Index: 302077 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5589. Min Act: -0.0002

Data Index: 1162304 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5672. Min Act: -0.0002

Data Index: 78395 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5551. Min Act: -0.0002

Data Index: 93072 (C4 (Web Text))

Max Activating Token Index: 798