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

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

Neuron 4328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1598539 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1554259 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1481816 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1493654 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1564202 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1645129 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1471187 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1650739 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.4076. Min Act: -0.0000

Data Index: 1469904 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1409167 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3826. Min Act: -0.0000

Data Index: 1415553 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1518059 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1600023 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1544029 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1568465 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3821. Min Act: -0.0000

Data Index: 1406801 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1486951 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.4526. Min Act: -0.0000

Data Index: 1510717 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1424629 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 1.6363. Min Range: -1.6363

Max Act: 1.3491. Min Act: -0.0000

Data Index: 1603069 (Python Code)

Max Activating Token Index: 13