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

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

Neuron 1574 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: 0.1415. Min Range: -0.1415

Max Act: 0.1395. Min Act: -0.0003

Data Index: 593007 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1415. Min Act: -0.0003

Data Index: 608924 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1343. Min Act: -0.0003

Data Index: 867662 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1335. Min Act: -0.0003

Data Index: 695505 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1033. Min Act: -0.0003

Data Index: 551382 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1134. Min Act: -0.0003

Data Index: 2187 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1118. Min Act: -0.0003

Data Index: 1088690 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1104. Min Act: -0.0003

Data Index: 1155461 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.0964. Min Act: -0.0003

Data Index: 358710 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1073. Min Act: -0.0003

Data Index: 628108 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1096. Min Act: -0.0003

Data Index: 452817 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1007. Min Act: -0.0003

Data Index: 135503 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.0929. Min Act: -0.0003

Data Index: 103374 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1044. Min Act: -0.0003

Data Index: 1206164 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1006. Min Act: -0.0003

Data Index: 15453 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.0999. Min Act: -0.0003

Data Index: 984723 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.0888. Min Act: -0.0003

Data Index: 433360 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1079. Min Act: -0.0003

Data Index: 333358 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1070. Min Act: -0.0003

Data Index: 1093785 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1415. Min Range: -0.1415

Max Act: 0.1023. Min Act: -0.0003

Data Index: 413934 (C4 (Web Text))

Max Activating Token Index: 73