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

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

Neuron 3808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.1720. Min Act: -0.0000

Data Index: 392481 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1147197 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1256267 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.0410. Min Act: -0.0000

Data Index: 307959 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1105025 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1250887 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8971. Min Act: -0.0000

Data Index: 458611 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8914. Min Act: -0.0000

Data Index: 825791 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1231579 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7532. Min Act: -0.0000

Data Index: 914749 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7176. Min Act: -0.0000

Data Index: 598285 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.6912. Min Act: -0.0000

Data Index: 140411 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7284. Min Act: -0.0000

Data Index: 902598 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1050549 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.6940. Min Act: -0.0000

Data Index: 220627 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.6967. Min Act: -0.0000

Data Index: 802560 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1286944 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7102. Min Act: -0.0000

Data Index: 371907 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.6785. Min Act: -0.0000

Data Index: 272953 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.7274. Min Act: -0.0000

Data Index: 125819 (C4 (Web Text))

Max Activating Token Index: 87