Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1806 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1055. Min Act: -0.0002

Data Index: 275725 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0002

Data Index: 843362 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1078690 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1017. Min Act: -0.0002

Data Index: 470560 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1029. Min Act: -0.0002

Data Index: 107763 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1006. Min Act: -0.0002

Data Index: 944653 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1008994 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1081160 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1011. Min Act: -0.0002

Data Index: 739302 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0965. Min Act: -0.0002

Data Index: 277620 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0971. Min Act: -0.0002

Data Index: 393695 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1105324 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0947. Min Act: -0.0002

Data Index: 953999 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0950. Min Act: -0.0002

Data Index: 711311 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1060027 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0934. Min Act: -0.0002

Data Index: 34640 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1211310 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1274615 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0917. Min Act: -0.0002

Data Index: 855536 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1320584 (C4 (Web Text))

Max Activating Token Index: 895