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

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

Neuron 3445 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: 1.3581. Min Range: -1.3581

Max Act: 1.3581. Min Act: -0.0002

Data Index: 1138337 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2779. Min Act: -0.0002

Data Index: 337475 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2283. Min Act: -0.0002

Data Index: 664031 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2332. Min Act: -0.0002

Data Index: 393131 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2677. Min Act: -0.0003

Data Index: 532132 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2201. Min Act: -0.0002

Data Index: 814765 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2593. Min Act: -0.0002

Data Index: 500175 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2192. Min Act: -0.0002

Data Index: 645062 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1798. Min Act: -0.0002

Data Index: 1315226 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1784. Min Act: -0.0002

Data Index: 1193763 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1646. Min Act: -0.0002

Data Index: 282547 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.2204. Min Act: -0.0002

Data Index: 205579 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1403. Min Act: -0.0002

Data Index: 892592 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1443. Min Act: -0.0002

Data Index: 1224482 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1618. Min Act: -0.0002

Data Index: 168801 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1260. Min Act: -0.0002

Data Index: 1252414 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1608. Min Act: -0.0002

Data Index: 453123 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1328. Min Act: -0.0002

Data Index: 686736 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1465. Min Act: -0.0002

Data Index: 152232 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1574. Min Act: -0.0002

Data Index: 761447 (C4 (Web Text))

Max Activating Token Index: 867