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

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

Neuron 2754 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: 2.3785. Min Range: -2.3785

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1402885 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 2.3785. Min Range: -2.3785

Max Act: 2.3785. Min Act: -0.0000

Data Index: 1592960 (Python Code)

Max Activating Token Index: 873

Text #2

Max Range: 2.3785. Min Range: -2.3785

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1534575 (Python Code)

Max Activating Token Index: 361

Text #3

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.7036. Min Act: -0.0000

Data Index: 1628107 (Python Code)

Max Activating Token Index: 319

Text #4

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.7445. Min Act: -0.0000

Data Index: 1604706 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.6506. Min Act: -0.0000

Data Index: 1492592 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1431322 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1402767 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.6812. Min Act: -0.0000

Data Index: 1438873 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.5453. Min Act: 0.0000

Data Index: 1396777 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1630028 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1648021 (Python Code)

Max Activating Token Index: 525

Text #12

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.4872. Min Act: 0.0000

Data Index: 1404292 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1541718 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.4631. Min Act: 0.0000

Data Index: 1517895 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1371054 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1479529 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1598975 (Python Code)

Max Activating Token Index: 983

Text #18

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1636792 (Python Code)

Max Activating Token Index: 285

Text #19

Max Range: 2.3785. Min Range: -2.3785

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1393684 (Python Code)

Max Activating Token Index: 973