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

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

Neuron 1156 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1620297 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1619670 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1542258 (Python Code)

Max Activating Token Index: 726

Text #3

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1405636 (Python Code)

Max Activating Token Index: 435

Text #4

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1551941 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1554042 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1358. Min Act: 0.0001

Data Index: 1520118 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1398993 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1363564 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1644692 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1575005 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1486019 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1585643 (Python Code)

Max Activating Token Index: 417

Text #13

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1528539 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1449089 (Python Code)

Max Activating Token Index: 577

Text #15

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1372043 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 1.4261. Min Range: -1.4261

Max Act: 0.9772. Min Act: 0.0001

Data Index: 1526075 (Python Code)

Max Activating Token Index: 877

Text #17

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1633134 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1454141 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1534271 (Python Code)

Max Activating Token Index: 117