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

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

Neuron 1222 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0720. Min Range: -2.0720

Max Act: 2.0720. Min Act: -0.0000

Data Index: 351999 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.9099. Min Act: -0.0000

Data Index: 337589 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.7724. Min Act: -0.0000

Data Index: 974757 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.7872. Min Act: -0.0000

Data Index: 408620 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.6734. Min Act: -0.0000

Data Index: 419925 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.6558. Min Act: -0.0000

Data Index: 780508 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5116. Min Act: -0.0000

Data Index: 738450 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5973. Min Act: -0.0000

Data Index: 470814 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5840. Min Act: -0.0000

Data Index: 525265 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5652. Min Act: -0.0000

Data Index: 101415 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5696. Min Act: -0.0000

Data Index: 1009994 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.4507. Min Act: -0.0000

Data Index: 916890 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5312. Min Act: 0.0003

Data Index: 449864 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.4471. Min Act: -0.0000

Data Index: 1355309 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.4429. Min Act: -0.0000

Data Index: 766228 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1322489 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.3859. Min Act: -0.0000

Data Index: 998626 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.4697. Min Act: -0.0000

Data Index: 1243963 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.4325. Min Act: -0.0000

Data Index: 313667 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 2.0720. Min Range: -2.0720

Max Act: 1.4321. Min Act: -0.0000

Data Index: 737071 (C4 (Web Text))

Max Activating Token Index: 416