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

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

Neuron 4842 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1496061 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1528720 (Python Code)

Max Activating Token Index: 656

Text #2

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1641857 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1613215 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1408461 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1390316 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1498288 (Python Code)

Max Activating Token Index: 683

Text #7

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1453609 (Python Code)

Max Activating Token Index: 1014

Text #8

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1580610 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1547239 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1415438 (Python Code)

Max Activating Token Index: 754

Text #11

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1656894 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1459799 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1585452 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1400381 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1420602 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1630872 (Python Code)

Max Activating Token Index: 510

Text #17

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1595360 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1556592 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1649909 (Python Code)

Max Activating Token Index: 712