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

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

Neuron 5445 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.9698. Min Act: -0.0000

Data Index: 543553 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.7676. Min Act: -0.0000

Data Index: 243799 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.5618. Min Act: -0.0000

Data Index: 605428 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0145. Min Act: -0.0000

Data Index: 1479286 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.2876. Min Act: -0.0000

Data Index: 104602 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.3517. Min Act: -0.0000

Data Index: 1128793 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0239. Min Act: -0.0000

Data Index: 665190 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.1034. Min Act: -0.0000

Data Index: 548995 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9623. Min Act: -0.0000

Data Index: 449271 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9256. Min Act: -0.0000

Data Index: 908621 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1493931 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9718. Min Act: -0.0000

Data Index: 243201 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9743. Min Act: -0.0000

Data Index: 58179 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8153. Min Act: -0.0000

Data Index: 94446 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0397. Min Act: -0.0000

Data Index: 860315 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8957. Min Act: -0.0000

Data Index: 580960 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.1246. Min Act: -0.0000

Data Index: 471761 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8719. Min Act: -0.0000

Data Index: 925484 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8566. Min Act: -0.0000

Data Index: 1348034 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8832. Min Act: -0.0000

Data Index: 699394 (C4 (Web Text))

Max Activating Token Index: 342