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

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

Neuron 4138 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: 0.8513. Min Range: -0.8513

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1524077 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1403571 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1584368 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1596178 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1570757 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1566021 (Python Code)

Max Activating Token Index: 723

Text #6

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1542368 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1507933 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1518998 (Python Code)

Max Activating Token Index: 433

Text #9

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1649094 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1389123 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1484893 (Python Code)

Max Activating Token Index: 820

Text #12

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1522075 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1374713 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1587014 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1361297 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1561422 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1640650 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1396232 (Python Code)

Max Activating Token Index: 643

Text #19

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1455917 (Python Code)

Max Activating Token Index: 127