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

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

Neuron 2564 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0720. Min Range: -1.0720

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1113090 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1086490 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1155122 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1242551 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8178. Min Act: -0.0000

Data Index: 734533 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8430. Min Act: -0.0000

Data Index: 692966 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7799. Min Act: -0.0000

Data Index: 87952 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8238. Min Act: -0.0000

Data Index: 634468 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1045509 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8125. Min Act: -0.0000

Data Index: 343423 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1188536 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7495. Min Act: -0.0000

Data Index: 849013 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8134. Min Act: -0.0000

Data Index: 207875 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1270577 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1009852 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7601. Min Act: -0.0000

Data Index: 926247 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7011. Min Act: -0.0000

Data Index: 946888 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7230. Min Act: -0.0000

Data Index: 446752 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7023. Min Act: -0.0000

Data Index: 829693 (C4 (Web Text))

Max Activating Token Index: 677