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

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

Neuron 5340 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4626. Min Range: -1.4626

Max Act: 1.4626. Min Act: 0.0001

Data Index: 1581016 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 1.4626. Min Range: -1.4626

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1596232 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 1.4626. Min Range: -1.4626

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1591144 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.9442. Min Act: 0.0000

Data Index: 1365563 (Python Code)

Max Activating Token Index: 471

Text #4

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1404575 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.9923. Min Act: 0.0001

Data Index: 1430667 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.9346. Min Act: 0.0001

Data Index: 1438129 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1508469 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1366792 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1555877 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1508481 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8187. Min Act: 0.0000

Data Index: 1371383 (Python Code)

Max Activating Token Index: 415

Text #12

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1603439 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.7817. Min Act: 0.0000

Data Index: 811136 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1059928 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1411070 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1383141 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1418857 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.7668. Min Act: 0.0000

Data Index: 1631998 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 1.4626. Min Range: -1.4626

Max Act: 0.7618. Min Act: 0.0000

Data Index: 1640075 (Python Code)

Max Activating Token Index: 291