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

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

Neuron 1889 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: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0001

Data Index: 385218 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0983. Min Act: -0.0001

Data Index: 348947 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0978. Min Act: -0.0001

Data Index: 111571 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0955. Min Act: -0.0001

Data Index: 5258 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0895. Min Act: -0.0001

Data Index: 237420 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0923. Min Act: -0.0001

Data Index: 493857 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1141408 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0923. Min Act: -0.0001

Data Index: 193012 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0852. Min Act: -0.0001

Data Index: 639953 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0844. Min Act: -0.0001

Data Index: 540967 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1300919 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0863. Min Act: -0.0001

Data Index: 831987 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0847. Min Act: -0.0001

Data Index: 937042 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0840. Min Act: -0.0001

Data Index: 342229 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0811. Min Act: -0.0001

Data Index: 622638 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0844. Min Act: -0.0001

Data Index: 935845 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0831. Min Act: -0.0001

Data Index: 897224 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1146896 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1029101 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0813. Min Act: -0.0001

Data Index: 416655 (C4 (Web Text))

Max Activating Token Index: 274