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

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

Neuron 1074 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1217. Min Act: -0.0002

Data Index: 592710 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1079. Min Act: -0.0002

Data Index: 952226 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1212475 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0891. Min Act: -0.0002

Data Index: 302040 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1313674 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0972. Min Act: -0.0002

Data Index: 189816 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0885. Min Act: -0.0002

Data Index: 717099 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1140. Min Act: -0.0002

Data Index: 574157 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0873. Min Act: -0.0002

Data Index: 78819 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0875. Min Act: -0.0002

Data Index: 79750 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1119556 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0938. Min Act: -0.0002

Data Index: 925675 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0800. Min Act: -0.0002

Data Index: 545847 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1010. Min Act: -0.0002

Data Index: 292294 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0896. Min Act: -0.0002

Data Index: 206956 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1374849 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0881. Min Act: -0.0002

Data Index: 683476 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0853. Min Act: -0.0002

Data Index: 729938 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0737. Min Act: -0.0002

Data Index: 441837 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0917. Min Act: -0.0002

Data Index: 995582 (C4 (Web Text))

Max Activating Token Index: 249