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

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

Neuron 833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1155. Min Act: -0.0003

Data Index: 1158605 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1058. Min Act: -0.0003

Data Index: 1339433 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1030. Min Act: -0.0003

Data Index: 238355 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1007. Min Act: -0.0003

Data Index: 962944 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0957. Min Act: -0.0003

Data Index: 466260 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1027. Min Act: -0.0003

Data Index: 1352973 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0987. Min Act: -0.0003

Data Index: 331783 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0982. Min Act: -0.0002

Data Index: 120726 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1017. Min Act: -0.0003

Data Index: 992240 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0985. Min Act: -0.0003

Data Index: 50397 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0958. Min Act: -0.0003

Data Index: 872853 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1050274 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1093430 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0900. Min Act: -0.0003

Data Index: 133225 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0927. Min Act: -0.0003

Data Index: 648643 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1103595 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0872. Min Act: -0.0003

Data Index: 792888 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1163212 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0846. Min Act: -0.0003

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1105389 (C4 (Web Text))

Max Activating Token Index: 311