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

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

Neuron 5472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1094636 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1618125 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1521931 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0938. Min Act: -0.0001

Data Index: 574839 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1429765 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0978. Min Act: -0.0001

Data Index: 501938 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1545457 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0809. Min Act: -0.0001

Data Index: 875268 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1204806 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0859. Min Act: -0.0001

Data Index: 599906 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0903. Min Act: -0.0001

Data Index: 454124 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0832. Min Act: -0.0001

Data Index: 811373 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0860. Min Act: -0.0001

Data Index: 743857 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0832. Min Act: -0.0001

Data Index: 388380 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1545006 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0898. Min Act: -0.0001

Data Index: 188003 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1577908 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0819. Min Act: -0.0001

Data Index: 950721 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0767. Min Act: -0.0001

Data Index: 53042 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0746. Min Act: -0.0001

Data Index: 309442 (C4 (Web Text))

Max Activating Token Index: 825