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

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

Neuron 916 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: 0.0713. Min Range: -0.0713

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1364961 (Python Code)

Max Activating Token Index: 400

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0690. Min Act: -0.0003

Data Index: 226151 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0698. Min Act: -0.0003

Data Index: 772930 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1566903 (Python Code)

Max Activating Token Index: 861

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0676. Min Act: -0.0003

Data Index: 617899 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1565737 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1652612 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1560684 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1021731 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1439428 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1150533 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1437510 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1434545 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1424025 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1602999 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1443143 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1124262 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1383502 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1403401 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1614588 (Python Code)

Max Activating Token Index: 474