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

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

Neuron 1407 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1655790 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1507841 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1524707 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1385132 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1583232 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1126. Min Act: -0.0000

Data Index: 405886 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1634110 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1119985 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1061. Min Act: -0.0000

Data Index: 665543 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1364014 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1548218 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1238286 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0964. Min Act: -0.0000

Data Index: 972835 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0904. Min Act: 0.0000

Data Index: 297274 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0937. Min Act: -0.0000

Data Index: 957854 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0895. Min Act: -0.0000

Data Index: 88689 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1234081 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.0897. Min Act: -0.0000

Data Index: 713119 (C4 (Web Text))

Max Activating Token Index: 767