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

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

Neuron 5487 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: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0001

Data Index: 513254 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1001. Min Act: -0.0001

Data Index: 79745 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0947. Min Act: -0.0001

Data Index: 782041 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0928. Min Act: -0.0001

Data Index: 851526 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1108104 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0894. Min Act: -0.0001

Data Index: 404419 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0887. Min Act: -0.0001

Data Index: 466387 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1283824 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0908. Min Act: -0.0001

Data Index: 619260 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1241879 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0948. Min Act: -0.0001

Data Index: 45549 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0947. Min Act: -0.0001

Data Index: 787219 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0881. Min Act: -0.0001

Data Index: 597075 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0892. Min Act: -0.0001

Data Index: 258601 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0887. Min Act: -0.0001

Data Index: 860242 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1353397 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0880. Min Act: -0.0001

Data Index: 265927 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0849. Min Act: -0.0001

Data Index: 861216 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0867. Min Act: -0.0001

Data Index: 385105 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1355285 (C4 (Web Text))

Max Activating Token Index: 10