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

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

Neuron 849 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: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1183426 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0809. Min Act: -0.0003

Data Index: 1492789 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1589679 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1523925 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0761. Min Act: -0.0003

Data Index: 730929 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1613528 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0758. Min Act: -0.0003

Data Index: 931829 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1426625 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1563187 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1460783 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1462670 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1610822 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0713. Min Act: -0.0003

Data Index: 600077 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1643785 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1418140 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1541019 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0696. Min Act: -0.0003

Data Index: 709241 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0699. Min Act: -0.0003

Data Index: 485370 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1008667 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0726. Min Act: -0.0002

Data Index: 561546 (C4 (Web Text))

Max Activating Token Index: 820