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

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

Neuron 989 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.9293. Min Act: -0.0000

Data Index: 1498742 (Python Code)

Max Activating Token Index: 656

Text #1

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5486. Min Act: -0.0000

Data Index: 1609951 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5515. Min Act: -0.0000

Data Index: 1484737 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.6741. Min Act: -0.0000

Data Index: 1610518 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.6656. Min Act: -0.0000

Data Index: 1634680 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1370235 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1407837 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.4967. Min Act: -0.0000

Data Index: 1499798 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.6303. Min Act: -0.0000

Data Index: 1451165 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5984. Min Act: -0.0000

Data Index: 1417992 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5751. Min Act: -0.0000

Data Index: 1534398 (Python Code)

Max Activating Token Index: 651

Text #11

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5553. Min Act: -0.0000

Data Index: 1529983 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5454. Min Act: -0.0000

Data Index: 1499797 (Python Code)

Max Activating Token Index: 510

Text #13

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1382318 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5159. Min Act: -0.0000

Data Index: 1560296 (Python Code)

Max Activating Token Index: 930

Text #15

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5102. Min Act: -0.0000

Data Index: 1397632 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.5035. Min Act: -0.0000

Data Index: 1499988 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.3708. Min Act: -0.0000

Data Index: 1519530 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.4948. Min Act: -0.0000

Data Index: 1466306 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 2.9293. Min Range: -2.9293

Max Act: 2.4928. Min Act: -0.0000

Data Index: 1626900 (Python Code)

Max Activating Token Index: 275