Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1406 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1646554 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1637444 (Python Code)

Max Activating Token Index: 625

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1550312 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1469137 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1595020 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1412518 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1642773 (Python Code)

Max Activating Token Index: 958

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1589966 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1527745 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1488905 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1547740 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0680. Min Act: -0.0003

Data Index: 1532661 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1617585 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1390141 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1458951 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1558999 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1463587 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1366123 (Python Code)

Max Activating Token Index: 550

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1394520 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1390713 (Python Code)

Max Activating Token Index: 101