Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0655. Min Range: -1.0655

Max Act: 1.0655. Min Act: -0.0001

Data Index: 155505 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1095591 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8579. Min Act: -0.0001

Data Index: 1213454 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8730. Min Act: -0.0001

Data Index: 632662 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8519. Min Act: -0.0001

Data Index: 158023 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8076. Min Act: -0.0001

Data Index: 235787 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8150. Min Act: -0.0001

Data Index: 916151 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7844. Min Act: -0.0001

Data Index: 403589 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7786. Min Act: -0.0001

Data Index: 1126665 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7351. Min Act: -0.0001

Data Index: 885701 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7525. Min Act: -0.0001

Data Index: 80012 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7700. Min Act: -0.0001

Data Index: 845658 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7032. Min Act: -0.0001

Data Index: 1005418 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6803. Min Act: -0.0001

Data Index: 378305 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7210. Min Act: -0.0001

Data Index: 991940 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1352672 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6905. Min Act: -0.0001

Data Index: 185276 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6903. Min Act: -0.0001

Data Index: 54829 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7005. Min Act: -0.0001

Data Index: 595183 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6815. Min Act: -0.0001

Data Index: 843067 (C4 (Web Text))

Max Activating Token Index: 889