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

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

Neuron 356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1416420 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1400208 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1406308 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1629098 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1403256 (Python Code)

Max Activating Token Index: 372

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1402287 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1646042 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1565031 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0662. Min Act: -0.0002

Data Index: 618037 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1393681 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1608033 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1418586 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0645. Min Act: -0.0002

Data Index: 204565 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1450824 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1625709 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1521632 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1469835 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1456891 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1466364 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1634683 (Python Code)

Max Activating Token Index: 201