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

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

Neuron 844 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4492. Min Act: -0.0004

Data Index: 735505 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4144. Min Act: -0.0004

Data Index: 36580 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4085. Min Act: -0.0004

Data Index: 667449 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3694. Min Act: -0.0004

Data Index: 695379 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4094. Min Act: -0.0004

Data Index: 1048490 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3876. Min Act: -0.0004

Data Index: 331301 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4281. Min Act: -0.0004

Data Index: 977116 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3706. Min Act: -0.0004

Data Index: 1308668 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3666. Min Act: -0.0004

Data Index: 608935 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4159. Min Act: -0.0004

Data Index: 318907 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4125. Min Act: -0.0004

Data Index: 1064602 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3597. Min Act: -0.0004

Data Index: 558223 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3822. Min Act: -0.0004

Data Index: 954963 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3884. Min Act: -0.0004

Data Index: 194975 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3628. Min Act: -0.0004

Data Index: 675857 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3875. Min Act: -0.0004

Data Index: 1270078 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4291. Min Act: -0.0004

Data Index: 702365 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3968. Min Act: -0.0004

Data Index: 533999 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3974. Min Act: -0.0004

Data Index: 990126 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3801. Min Act: -0.0004

Data Index: 1179611 (C4 (Web Text))

Max Activating Token Index: 674