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

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

Neuron 3533 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1415836 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1407903 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1610308 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1410697 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1416701 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1562841 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1514338 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1637777 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1497588 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1523907 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1383892 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1469487 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1436394 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1625886 (Python Code)

Max Activating Token Index: 687

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1606688 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1071588 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1527508 (Python Code)

Max Activating Token Index: 406

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1637519 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1546532 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1394949 (Python Code)

Max Activating Token Index: 916