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

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

Neuron 4324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1039597 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1174229 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1254. Min Act: -0.0001

Data Index: 960356 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1168. Min Act: -0.0001

Data Index: 847158 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1069. Min Act: -0.0001

Data Index: 949586 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1032781 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1064. Min Act: -0.0001

Data Index: 252614 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1143643 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1085. Min Act: -0.0001

Data Index: 205430 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1059. Min Act: -0.0001

Data Index: 673023 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0991. Min Act: -0.0001

Data Index: 363606 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1000. Min Act: -0.0001

Data Index: 269347 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1069. Min Act: -0.0001

Data Index: 753853 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0996. Min Act: -0.0001

Data Index: 19440 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1088. Min Act: -0.0001

Data Index: 756714 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0988. Min Act: -0.0001

Data Index: 833788 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0988. Min Act: -0.0001

Data Index: 439859 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0880. Min Act: -0.0001

Data Index: 76094 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0976. Min Act: -0.0001

Data Index: 506949 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0919. Min Act: -0.0001

Data Index: 457654 (C4 (Web Text))

Max Activating Token Index: 447