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

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

Neuron 25 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3826. Min Act: -0.0000

Data Index: 1531008 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1576825 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1420898 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1402478 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1413404 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1527113 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1502472 (Python Code)

Max Activating Token Index: 559

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1411237 (Python Code)

Max Activating Token Index: 783

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1057128 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7874. Min Act: 0.0000

Data Index: 1571134 (Python Code)

Max Activating Token Index: 761

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1580270 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1368647 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7593. Min Act: 0.0000

Data Index: 1383410 (Python Code)

Max Activating Token Index: 275

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 103

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7528. Min Act: 0.0000

Data Index: 1550866 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1474698 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1398547 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1503691 (Python Code)

Max Activating Token Index: 557

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1579077 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1505828 (Python Code)

Max Activating Token Index: 854