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

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

Neuron 3622 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1402231 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1445. Min Act: 0.0000

Data Index: 1655552 (Python Code)

Max Activating Token Index: 783

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1502752 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1317. Min Act: -0.0000

Data Index: 371787 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1205. Min Act: 0.0000

Data Index: 1472609 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1596476 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1454459 (Python Code)

Max Activating Token Index: 798

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1526629 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1291547 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1030. Min Act: 0.0000

Data Index: 1630028 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1493976 (Python Code)

Max Activating Token Index: 538

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1124276 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0959. Min Act: 0.0000

Data Index: 1401707 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1530229 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1362505 (Python Code)

Max Activating Token Index: 959

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1628570 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1557482 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1641295 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1474117 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1065049 (C4 (Web Text))

Max Activating Token Index: 340