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

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

Neuron 365 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1381195 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1625815 (Python Code)

Max Activating Token Index: 711

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1524192 (Python Code)

Max Activating Token Index: 494

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1470050 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1542376 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1361014 (Python Code)

Max Activating Token Index: 902

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1373244 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1411469 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1440669 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1424448 (Python Code)

Max Activating Token Index: 481

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0561. Min Act: -0.0002

Data Index: 35172 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1473105 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1608458 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1588103 (Python Code)

Max Activating Token Index: 440

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1347944 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1433600 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1645483 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1445593 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1029903 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1138095 (C4 (Web Text))

Max Activating Token Index: 811