Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 85 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1196. Min Act: -0.0001

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1157. Min Act: -0.0001

Data Index: 719829 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1013122 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0957. Min Act: -0.0001

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1058991 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1096948 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1004434 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0864. Min Act: -0.0001

Data Index: 24361 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0827. Min Act: -0.0001

Data Index: 705109 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1060950 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0706. Min Act: -0.0001

Data Index: 276557 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0774. Min Act: -0.0001

Data Index: 882570 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0776. Min Act: -0.0001

Data Index: 75001 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0769. Min Act: -0.0001

Data Index: 791012 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0708. Min Act: -0.0001

Data Index: 880167 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0760. Min Act: -0.0001

Data Index: 61687 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1150240 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1056553 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0810. Min Act: -0.0001

Data Index: 622272 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1202450 (C4 (Web Text))

Max Activating Token Index: 710