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

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

Neuron 3773 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: 1.2086. Min Range: -1.2086

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1640702 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 1.2086. Min Range: -1.2086

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1426977 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 1.2086. Min Range: -1.2086

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1578532 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 1.2086. Min Range: -1.2086

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1458340 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1506669 (Python Code)

Max Activating Token Index: 753

Text #5

Max Range: 1.2086. Min Range: -1.2086

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1485522 (Python Code)

Max Activating Token Index: 867

Text #6

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1556648 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1433962 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1493227 (Python Code)

Max Activating Token Index: 430

Text #9

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1462713 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1486418 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1406619 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1118028 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1578730 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1528810 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1384800 (Python Code)

Max Activating Token Index: 233

Text #16

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1372861 (Python Code)

Max Activating Token Index: 866

Text #17

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1574505 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1375840 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.2086. Min Range: -1.2086

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1490367 (Python Code)

Max Activating Token Index: 617