Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 87 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1227981 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1013520 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1357060 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0001

Data Index: 351740 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1464069 (Python Code)

Max Activating Token Index: 544

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0853. Min Act: -0.0001

Data Index: 349803 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0840. Min Act: -0.0001

Data Index: 972624 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0824. Min Act: -0.0001

Data Index: 982570 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0815. Min Act: -0.0001

Data Index: 258938 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0806. Min Act: -0.0001

Data Index: 215936 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0832. Min Act: -0.0001

Data Index: 763507 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1348244 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1034312 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0757. Min Act: -0.0001

Data Index: 877001 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1219471 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0784. Min Act: -0.0001

Data Index: 455656 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0782. Min Act: -0.0001

Data Index: 267620 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0746. Min Act: -0.0001

Data Index: 755985 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0770. Min Act: -0.0001

Data Index: 927743 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0738. Min Act: -0.0001

Data Index: 922496 (C4 (Web Text))

Max Activating Token Index: 674