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

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

Neuron 2624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1018099 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1447. Min Act: -0.0001

Data Index: 621109 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1056511 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1207. Min Act: -0.0001

Data Index: 780075 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1196. Min Act: -0.0001

Data Index: 430496 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1184. Min Act: -0.0001

Data Index: 443738 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1286161 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1104. Min Act: -0.0001

Data Index: 772461 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1133. Min Act: -0.0001

Data Index: 414871 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1129. Min Act: -0.0001

Data Index: 338645 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1136. Min Act: -0.0001

Data Index: 127269 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1088. Min Act: -0.0001

Data Index: 560451 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1348133 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1080. Min Act: -0.0001

Data Index: 124264 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1045. Min Act: -0.0001

Data Index: 756703 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1107. Min Act: -0.0001

Data Index: 204318 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1114780 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1043. Min Act: -0.0001

Data Index: 3816 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1035. Min Act: -0.0001

Data Index: 623450 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1013. Min Act: -0.0001

Data Index: 505585 (C4 (Web Text))

Max Activating Token Index: 1022