Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0857. Min Range: -1.0857

Max Act: 1.0857. Min Act: -0.0001

Data Index: 519895 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.0857. Min Range: -1.0857

Max Act: 1.0166. Min Act: -0.0001

Data Index: 205268 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.9859. Min Act: -0.0001

Data Index: 1248623 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.9482. Min Act: -0.0001

Data Index: 977796 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.9389. Min Act: -0.0001

Data Index: 111148 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1058285 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1281999 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.9349. Min Act: -0.0001

Data Index: 1090013 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8998. Min Act: -0.0001

Data Index: 846929 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1342109 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8680. Min Act: -0.0001

Data Index: 541327 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8803. Min Act: -0.0001

Data Index: 692881 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.9182. Min Act: -0.0001

Data Index: 1212871 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.9074. Min Act: -0.0001

Data Index: 346836 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8799. Min Act: -0.0000

Data Index: 620263 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8477. Min Act: -0.0001

Data Index: 379079 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1085415 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8598. Min Act: -0.0001

Data Index: 93076 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8356. Min Act: -0.0001

Data Index: 626616 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 1.0857. Min Range: -1.0857

Max Act: 0.8885. Min Act: -0.0001

Data Index: 634508 (C4 (Web Text))

Max Activating Token Index: 66