Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 15 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.6016. Min Act: -0.0001

Data Index: 1432645 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.4154. Min Act: -0.0001

Data Index: 1475100 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0080. Min Act: -0.0001

Data Index: 1598659 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1455819 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1399320 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9289. Min Act: -0.0001

Data Index: 1364417 (Python Code)

Max Activating Token Index: 110

Text #6

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9282. Min Act: -0.0001

Data Index: 1572434 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9266. Min Act: -0.0001

Data Index: 1606477 (Python Code)

Max Activating Token Index: 501

Text #8

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1545347 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8734. Min Act: -0.0001

Data Index: 1456685 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1499036 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1376366 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8953. Min Act: -0.0001

Data Index: 1541437 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1414431 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8804. Min Act: -0.0001

Data Index: 1565849 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1374867 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1617542 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8376. Min Act: -0.0001

Data Index: 1513264 (Python Code)

Max Activating Token Index: 396

Text #18

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7987. Min Act: -0.0001

Data Index: 1401274 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1563412 (Python Code)

Max Activating Token Index: 335