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

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

Neuron 4492 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1327. Min Act: -0.0001

Data Index: 456016 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1282. Min Act: -0.0001

Data Index: 815771 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1096. Min Act: -0.0001

Data Index: 287723 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1009. Min Act: -0.0001

Data Index: 63863 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1014. Min Act: -0.0001

Data Index: 882516 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1064755 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0997. Min Act: -0.0001

Data Index: 692767 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1409736 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1138402 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0891. Min Act: -0.0001

Data Index: 459581 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0888. Min Act: -0.0001

Data Index: 103529 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0887. Min Act: -0.0001

Data Index: 693816 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0838. Min Act: -0.0001

Data Index: 189131 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0858. Min Act: -0.0001

Data Index: 840592 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0826. Min Act: -0.0001

Data Index: 89159 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1008533 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0737. Min Act: -0.0001

Data Index: 850139 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0727. Min Act: -0.0001

Data Index: 734614 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0703. Min Act: -0.0001

Data Index: 335630 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1078388 (C4 (Web Text))

Max Activating Token Index: 518