Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2908 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1451128 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2330. Min Act: -0.0000

Data Index: 543140 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1554239 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1486743 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1726. Min Act: -0.0000

Data Index: 131384 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1609778 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1454909 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1363512 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1423871 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1555238 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1505686 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1355101 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1532498 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1562. Min Act: -0.0000

Data Index: 621953 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1580616 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1528425 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1459562 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1624116 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1389966 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1622348 (Python Code)

Max Activating Token Index: 787