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

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

Neuron 3145 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: 1.3428. Min Range: -1.3428

Max Act: 1.3428. Min Act: -0.0000

Data Index: 659226 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.3315. Min Act: -0.0000

Data Index: 953578 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1650193 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1640139 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1433448 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1603644 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1361068 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1758. Min Act: -0.0000

Data Index: 930598 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1490111 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1524118 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1429480 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1447522 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1365. Min Act: -0.0000

Data Index: 696998 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1243. Min Act: -0.0000

Data Index: 487677 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1584004 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1624293 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1413686 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1457414 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1492345 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1432360 (Python Code)

Max Activating Token Index: 509