Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1015 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.7114. Min Act: -0.0000

Data Index: 1581279 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1520047 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1585556 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1363984 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1596248 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.4806. Min Act: 0.0002

Data Index: 1597927 (Python Code)

Max Activating Token Index: 704

Text #6

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1463472 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.5249. Min Act: 0.0000

Data Index: 1574925 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1426050 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.3945. Min Act: -0.0000

Data Index: 1608331 (Python Code)

Max Activating Token Index: 953

Text #10

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.3828. Min Act: 0.0001

Data Index: 1583650 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.2768. Min Act: 0.0000

Data Index: 1613267 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.3740. Min Act: -0.0000

Data Index: 1411131 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1448418 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1417246 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1582338 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.2623. Min Act: -0.0001

Data Index: 1628993 (Python Code)

Max Activating Token Index: 920

Text #17

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.2619. Min Act: -0.0001

Data Index: 1617073 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1544938 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 1.7114. Min Range: -1.7114

Max Act: 1.1782. Min Act: -0.0001

Data Index: 1619665 (Python Code)

Max Activating Token Index: 305