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

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

Neuron 496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2765. Min Range: -10.2765

Max Act: 10.2765. Min Act: -0.0000

Data Index: 129808 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.6158. Min Act: -0.0000

Data Index: 754741 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.3081. Min Act: -0.0000

Data Index: 696188 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.1148. Min Act: -0.0000

Data Index: 310886 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.2434. Min Act: -0.0000

Data Index: 896375 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.9126. Min Act: -0.0000

Data Index: 121219 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.3536. Min Act: -0.0000

Data Index: 1285680 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.1878. Min Act: -0.0000

Data Index: 248308 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.7381. Min Act: -0.0000

Data Index: 916181 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.6759. Min Act: -0.0000

Data Index: 32165 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.8149. Min Act: -0.0000

Data Index: 827058 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.2387. Min Act: -0.0000

Data Index: 352941 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 10.2765. Min Range: -10.2765

Max Act: 9.0756. Min Act: -0.0000

Data Index: 1082510 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.5383. Min Act: -0.0000

Data Index: 898366 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.5350. Min Act: -0.0000

Data Index: 421006 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.1597. Min Act: -0.0000

Data Index: 1291767 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.4562. Min Act: -0.0000

Data Index: 497005 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.2285. Min Act: -0.0000

Data Index: 713647 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.0440. Min Act: -0.0000

Data Index: 845971 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 10.2765. Min Range: -10.2765

Max Act: 8.2116. Min Act: -0.0000

Data Index: 197066 (C4 (Web Text))

Max Activating Token Index: 393