Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2172 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1168. Min Act: -0.0003

Data Index: 1093082 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1282. Min Act: -0.0003

Data Index: 743601 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1196. Min Act: -0.0003

Data Index: 749075 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1191. Min Act: -0.0003

Data Index: 236171 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1194. Min Act: -0.0003

Data Index: 1114107 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1063. Min Act: -0.0003

Data Index: 217733 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1106. Min Act: -0.0003

Data Index: 131922 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1132. Min Act: -0.0003

Data Index: 921674 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1071180 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0954. Min Act: -0.0003

Data Index: 464681 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0964. Min Act: -0.0003

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1008. Min Act: -0.0003

Data Index: 155710 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1551757 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1132566 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0868. Min Act: -0.0003

Data Index: 930476 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0950. Min Act: -0.0003

Data Index: 338613 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0876. Min Act: -0.0003

Data Index: 845493 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1012009 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0932. Min Act: -0.0003

Data Index: 15114 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0827. Min Act: -0.0003

Data Index: 805735 (C4 (Web Text))

Max Activating Token Index: 963