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

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

Neuron 4258 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1514005 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1629367 (Python Code)

Max Activating Token Index: 253

Text #2

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1581525 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1446404 (Python Code)

Max Activating Token Index: 902

Text #4

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1174535 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1642455 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1581049 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1454107 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1621730 (Python Code)

Max Activating Token Index: 304

Text #9

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1642489 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1403687 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1474288 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1521231 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1641570 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1407770 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1366286 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1214. Min Act: -0.0000

Data Index: 43633 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1384188 (Python Code)

Max Activating Token Index: 498

Text #18

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1563261 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 1.3836. Min Range: -1.3836

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1516939 (Python Code)

Max Activating Token Index: 388