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

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

Neuron 2653 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0636. Min Act: -0.0001

Data Index: 521668 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1437201 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0001

Data Index: 572186 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1540053 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1650583 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1372743 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1468920 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1441851 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1446658 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0556. Min Act: -0.0001

Data Index: 592639 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0514. Min Act: -0.0001

Data Index: 955327 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1302382 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1362981 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1463174 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0547. Min Act: -0.0001

Data Index: 658454 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1453673 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0517. Min Act: -0.0001

Data Index: 116546 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1488851 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1414526 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1375201 (Python Code)

Max Activating Token Index: 6