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

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

Neuron 1617 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: 0.0643. Min Range: -0.0643

Max Act: 0.0634. Min Act: -0.0003

Data Index: 884166 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0003

Data Index: 951350 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0628. Min Act: -0.0003

Data Index: 129838 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0600. Min Act: -0.0003

Data Index: 370908 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0571. Min Act: -0.0003

Data Index: 547119 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0611. Min Act: -0.0003

Data Index: 640061 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1278105 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0605. Min Act: -0.0003

Data Index: 47375 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1161080 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0615. Min Act: -0.0003

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1251754 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1096275 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0562. Min Act: -0.0003

Data Index: 475777 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0610. Min Act: -0.0003

Data Index: 339145 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1082792 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0570. Min Act: -0.0003

Data Index: 268570 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0588. Min Act: -0.0003

Data Index: 858503 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0586. Min Act: -0.0003

Data Index: 176224 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0612. Min Act: -0.0003

Data Index: 695231 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0583. Min Act: -0.0003

Data Index: 277460 (C4 (Web Text))

Max Activating Token Index: 616