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

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

Neuron 4484 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.1248. Min Act: -0.0000

Data Index: 837126 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.0366. Min Act: -0.0000

Data Index: 781555 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.1440. Min Act: -0.0000

Data Index: 780199 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9256. Min Act: -0.0000

Data Index: 594345 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9274. Min Act: -0.0000

Data Index: 828219 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9647. Min Act: -0.0000

Data Index: 135286 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8602. Min Act: -0.0000

Data Index: 716909 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8984. Min Act: -0.0000

Data Index: 687109 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8791. Min Act: -0.0000

Data Index: 519900 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8968. Min Act: -0.0000

Data Index: 988133 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1025642 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8138. Min Act: -0.0000

Data Index: 4229 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1158916 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7928. Min Act: -0.0000

Data Index: 413578 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7614. Min Act: -0.0000

Data Index: 139524 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8119. Min Act: -0.0000

Data Index: 669666 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7585. Min Act: -0.0000

Data Index: 720799 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1067672 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7911. Min Act: -0.0000

Data Index: 708429 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7566. Min Act: -0.0000

Data Index: 184551 (C4 (Web Text))

Max Activating Token Index: 146