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

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

Neuron 2407 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: 0.1197. Min Range: -0.1197

Max Act: 0.1109. Min Act: -0.0003

Data Index: 480699 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1099. Min Act: -0.0003

Data Index: 1340435 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1152. Min Act: -0.0003

Data Index: 760929 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1068. Min Act: -0.0003

Data Index: 1024515 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1052. Min Act: -0.0003

Data Index: 407414 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1021526 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0898. Min Act: -0.0003

Data Index: 353807 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1065. Min Act: -0.0003

Data Index: 1257036 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1027. Min Act: -0.0003

Data Index: 142534 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1051. Min Act: -0.0003

Data Index: 737545 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1197. Min Act: -0.0003

Data Index: 644807 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0997. Min Act: -0.0003

Data Index: 201405 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0935. Min Act: -0.0003

Data Index: 127431 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1002. Min Act: -0.0003

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0961. Min Act: -0.0003

Data Index: 232278 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0989. Min Act: -0.0003

Data Index: 1060858 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1053255 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1064. Min Act: -0.0003

Data Index: 745625 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0978. Min Act: -0.0003

Data Index: 1349031 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0958. Min Act: -0.0003

Data Index: 626748 (C4 (Web Text))

Max Activating Token Index: 684