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

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

Neuron 4180 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0000

Data Index: 870636 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1289. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1123. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1152. Min Act: -0.0001

Data Index: 177300 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0930. Min Act: -0.0001

Data Index: 549723 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0949. Min Act: -0.0001

Data Index: 174227 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1120258 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0972. Min Act: -0.0001

Data Index: 516545 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0850. Min Act: -0.0000

Data Index: 451098 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0858. Min Act: -0.0000

Data Index: 260789 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0727. Min Act: -0.0000

Data Index: 409817 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0804. Min Act: -0.0001

Data Index: 748073 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1289211 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1074883 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0736. Min Act: -0.0001

Data Index: 573601 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0827. Min Act: -0.0001

Data Index: 885967 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0721. Min Act: -0.0001

Data Index: 759136 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1061522 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.0631. Min Act: -0.0001

Data Index: 505950 (C4 (Web Text))

Max Activating Token Index: 229