Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.0285. Min Range: -6.0285

Max Act: 6.0285. Min Act: -0.0000

Data Index: 1638280 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 6.0285. Min Range: -6.0285

Max Act: 5.5043. Min Act: -0.0000

Data Index: 1511361 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 6.0285. Min Range: -6.0285

Max Act: 5.2136. Min Act: -0.0000

Data Index: 1452806 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 6.0285. Min Range: -6.0285

Max Act: 5.1476. Min Act: -0.0000

Data Index: 1390100 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 6.0285. Min Range: -6.0285

Max Act: 4.3828. Min Act: -0.0000

Data Index: 1626461 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 6.0285. Min Range: -6.0285

Max Act: 4.0705. Min Act: -0.0000

Data Index: 1518211 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.7844. Min Act: -0.0000

Data Index: 1653336 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.7935. Min Act: -0.0000

Data Index: 1650342 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 6.0285. Min Range: -6.0285

Max Act: 4.0565. Min Act: -0.0000

Data Index: 1545866 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.6577. Min Act: -0.0000

Data Index: 1499546 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.2828. Min Act: -0.0000

Data Index: 1405129 (Python Code)

Max Activating Token Index: 501

Text #11

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.1926. Min Act: -0.0000

Data Index: 1535294 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.5482. Min Act: -0.0000

Data Index: 1485430 (Python Code)

Max Activating Token Index: 985

Text #13

Max Range: 6.0285. Min Range: -6.0285

Max Act: 2.9478. Min Act: -0.0000

Data Index: 1470419 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.2514. Min Act: -0.0000

Data Index: 1418616 (Python Code)

Max Activating Token Index: 865

Text #15

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.3502. Min Act: -0.0000

Data Index: 1582568 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.5131. Min Act: -0.0000

Data Index: 1423642 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.4613. Min Act: -0.0000

Data Index: 1425831 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.2663. Min Act: -0.0000

Data Index: 1494632 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 6.0285. Min Range: -6.0285

Max Act: 3.3860. Min Act: -0.0000

Data Index: 1429833 (Python Code)

Max Activating Token Index: 138