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

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

Neuron 1580 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: 0.1102. Min Range: -0.1102

Max Act: 0.1026. Min Act: -0.0003

Data Index: 397004 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0003

Data Index: 878898 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0934. Min Act: -0.0003

Data Index: 128810 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1046. Min Act: -0.0003

Data Index: 425466 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0804. Min Act: -0.0003

Data Index: 143562 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1298370 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0940. Min Act: -0.0003

Data Index: 522957 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0905. Min Act: -0.0003

Data Index: 430055 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0883. Min Act: -0.0003

Data Index: 596287 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0849. Min Act: -0.0003

Data Index: 901736 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0867. Min Act: -0.0003

Data Index: 457360 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0882. Min Act: -0.0003

Data Index: 647104 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0877. Min Act: -0.0003

Data Index: 1178054 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0875. Min Act: -0.0003

Data Index: 481573 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0899. Min Act: -0.0003

Data Index: 150042 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0852. Min Act: -0.0003

Data Index: 801186 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0830. Min Act: -0.0003

Data Index: 369549 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1217391 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0830. Min Act: -0.0003

Data Index: 930134 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1029653 (C4 (Web Text))

Max Activating Token Index: 739