Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3737 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.7667. Min Act: -0.0001

Data Index: 361504 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.4643. Min Act: -0.0000

Data Index: 1283627 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.4297. Min Act: -0.0001

Data Index: 659553 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.3295. Min Act: -0.0001

Data Index: 1023573 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2821. Min Act: -0.0001

Data Index: 422551 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2891. Min Act: -0.0001

Data Index: 1358212 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.3468. Min Act: -0.0001

Data Index: 149819 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2746. Min Act: -0.0001

Data Index: 86578 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.3330. Min Act: -0.0001

Data Index: 508558 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2578. Min Act: -0.0001

Data Index: 387900 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.3877. Min Act: -0.0001

Data Index: 767637 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2904. Min Act: -0.0001

Data Index: 1257621 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2147. Min Act: -0.0001

Data Index: 431632 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.1966. Min Act: -0.0001

Data Index: 792933 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.1217. Min Act: -0.0001

Data Index: 337838 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2592. Min Act: -0.0001

Data Index: 1288822 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2470. Min Act: -0.0001

Data Index: 523230 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1274934 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.2976. Min Act: -0.0001

Data Index: 1349734 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.7667. Min Range: -1.7667

Max Act: 1.1768. Min Act: -0.0001

Data Index: 997404 (C4 (Web Text))

Max Activating Token Index: 216