Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 665 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3662. Min Act: -0.0003

Data Index: 1496378 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3401. Min Act: -0.0003

Data Index: 1186757 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3336. Min Act: -0.0003

Data Index: 1367609 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3247. Min Act: -0.0003

Data Index: 653543 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3026. Min Act: -0.0003

Data Index: 194035 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2949. Min Act: -0.0003

Data Index: 475960 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2877. Min Act: -0.0002

Data Index: 487298 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2586. Min Act: -0.0003

Data Index: 1588139 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2840. Min Act: -0.0003

Data Index: 1648817 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2827. Min Act: -0.0003

Data Index: 703154 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2819. Min Act: -0.0003

Data Index: 1543856 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2989. Min Act: -0.0003

Data Index: 114658 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2621. Min Act: -0.0003

Data Index: 1162287 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2676. Min Act: -0.0003

Data Index: 1488566 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2654. Min Act: -0.0003

Data Index: 1449784 (Python Code)

Max Activating Token Index: 449

Text #15

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2543. Min Act: -0.0003

Data Index: 157004 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2633. Min Act: -0.0003

Data Index: 1620217 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2562. Min Act: -0.0003

Data Index: 1443788 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2602. Min Act: -0.0003

Data Index: 1615692 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2531. Min Act: -0.0003

Data Index: 1371905 (Python Code)

Max Activating Token Index: 845