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

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

Neuron 4266 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: 0.8581. Min Range: -0.8581

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1391102 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1409889 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1458352 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6423. Min Act: 0.0000

Data Index: 1407541 (Python Code)

Max Activating Token Index: 498

Text #4

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1627483 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1438568 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1543841 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1417476 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1364200 (Python Code)

Max Activating Token Index: 148

Text #9

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1369905 (Python Code)

Max Activating Token Index: 764

Text #10

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1454910 (Python Code)

Max Activating Token Index: 652

Text #11

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1488790 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1420850 (Python Code)

Max Activating Token Index: 729

Text #13

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1446281 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1532632 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1639944 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1442475 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1463066 (Python Code)

Max Activating Token Index: 455

Text #18

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1550852 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1575829 (Python Code)

Max Activating Token Index: 233