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

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

Neuron 690 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: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0003

Data Index: 1605776 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1372329 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1385338 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1588055 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1473163 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1547316 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1509874 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1503500 (Python Code)

Max Activating Token Index: 33

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1522598 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1520809 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1429181 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1397405 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1621738 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1388885 (Python Code)

Max Activating Token Index: 592

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1547079 (Python Code)

Max Activating Token Index: 111

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1456466 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1516095 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1486717 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1476855 (Python Code)

Max Activating Token Index: 661

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1371823 (Python Code)

Max Activating Token Index: 548