Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 413 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1208000 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1059550 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0636. Min Act: -0.0004

Data Index: 1203161 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0619. Min Act: -0.0003

Data Index: 286826 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0601. Min Act: -0.0003

Data Index: 443167 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0611. Min Act: -0.0003

Data Index: 338873 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1268003 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0579. Min Act: -0.0003

Data Index: 850386 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0571. Min Act: -0.0003

Data Index: 100079 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0570. Min Act: -0.0004

Data Index: 985945 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0568. Min Act: -0.0004

Data Index: 428116 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0568. Min Act: -0.0003

Data Index: 911111 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0550. Min Act: -0.0004

Data Index: 186757 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0589. Min Act: -0.0003

Data Index: 52987 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0553. Min Act: -0.0003

Data Index: 530502 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1062927 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1031471 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0539. Min Act: -0.0004

Data Index: 606952 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1032624 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0534. Min Act: -0.0003

Data Index: 480816 (C4 (Web Text))

Max Activating Token Index: 830