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

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

Neuron 942 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5532. Min Range: -3.5532

Max Act: 3.4173. Min Act: -0.0000

Data Index: 1611031 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 3.5532. Min Range: -3.5532

Max Act: 3.5532. Min Act: -0.0001

Data Index: 1455685 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.9824. Min Act: -0.0000

Data Index: 1623399 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1559526 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.6037. Min Act: -0.0000

Data Index: 1593799 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.8684. Min Act: -0.0001

Data Index: 1441367 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.7535. Min Act: -0.0000

Data Index: 1598430 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.8964. Min Act: -0.0000

Data Index: 1481495 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.7219. Min Act: -0.0001

Data Index: 1441867 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.4433. Min Act: -0.0001

Data Index: 1434431 (Python Code)

Max Activating Token Index: 763

Text #10

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.5735. Min Act: -0.0001

Data Index: 1442453 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.2545. Min Act: -0.0000

Data Index: 1417781 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.6328. Min Act: -0.0000

Data Index: 1413348 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.4875. Min Act: -0.0000

Data Index: 1571503 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.3418. Min Act: -0.0000

Data Index: 1651526 (Python Code)

Max Activating Token Index: 933

Text #15

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.5995. Min Act: -0.0001

Data Index: 1584651 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.7246. Min Act: -0.0000

Data Index: 1431311 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.4525. Min Act: -0.0001

Data Index: 1612972 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.3439. Min Act: -0.0000

Data Index: 1507067 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 3.5532. Min Range: -3.5532

Max Act: 2.5521. Min Act: -0.0001

Data Index: 1501875 (Python Code)

Max Activating Token Index: 479