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

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

Neuron 4908 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.8859. Min Act: -0.0000

Data Index: 233727 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.8546. Min Act: 0.0000

Data Index: 1212769 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.8015. Min Act: -0.0000

Data Index: 958168 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1253131 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6812. Min Act: -0.0000

Data Index: 170967 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.7448. Min Act: -0.0000

Data Index: 346949 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.7435. Min Act: 0.0001

Data Index: 834464 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.7293. Min Act: -0.0000

Data Index: 944878 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6948. Min Act: 0.0001

Data Index: 1294818 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1005890 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6801. Min Act: -0.0000

Data Index: 322697 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.7307. Min Act: -0.0000

Data Index: 267649 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6407. Min Act: -0.0000

Data Index: 635110 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6577. Min Act: 0.0001

Data Index: 844031 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1042385 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6225. Min Act: 0.0005

Data Index: 134906 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6085. Min Act: -0.0000

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6064. Min Act: -0.0000

Data Index: 976004 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6269. Min Act: -0.0000

Data Index: 494858 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.8859. Min Range: -0.8859

Max Act: 0.6166. Min Act: -0.0000

Data Index: 150645 (C4 (Web Text))

Max Activating Token Index: 33