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

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

Neuron 109 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: 1.5444. Min Range: -1.5444

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1510753 (Python Code)

Max Activating Token Index: 121

Text #1

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1478453 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1540030 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1470569 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1486047 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1450896 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1466886 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1464423 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1649608 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1592779 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1562450 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1476117 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1487899 (Python Code)

Max Activating Token Index: 300

Text #13

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1433432 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1458211 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1590112 (Python Code)

Max Activating Token Index: 989

Text #16

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1631064 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1525965 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 1.5444. Min Range: -1.5444

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1628954 (Python Code)

Max Activating Token Index: 848

Text #19

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1421646 (Python Code)

Max Activating Token Index: 68