Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 956 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0002

Data Index: 307956 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1105. Min Act: -0.0002

Data Index: 265260 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1156. Min Act: -0.0002

Data Index: 846557 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1065. Min Act: -0.0002

Data Index: 368428 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1254400 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1056287 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1069310 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1076. Min Act: -0.0002

Data Index: 924785 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1115855 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1178226 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1052. Min Act: -0.0002

Data Index: 455494 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1043. Min Act: -0.0002

Data Index: 826114 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1044. Min Act: -0.0002

Data Index: 618111 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1054. Min Act: -0.0002

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1042. Min Act: -0.0002

Data Index: 177272 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1156676 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1504722 (Python Code)

Max Activating Token Index: 447

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1033. Min Act: -0.0002

Data Index: 740269 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1232091 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1277197 (C4 (Web Text))

Max Activating Token Index: 679