Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.6056. Min Act: -0.0003

Data Index: 339426 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5869. Min Act: -0.0003

Data Index: 14268 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5817. Min Act: -0.0003

Data Index: 193273 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5713. Min Act: -0.0003

Data Index: 839462 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5691. Min Act: -0.0003

Data Index: 952061 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5379. Min Act: -0.0003

Data Index: 1068587 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5326. Min Act: -0.0003

Data Index: 309426 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5244. Min Act: -0.0003

Data Index: 458885 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5288. Min Act: -0.0003

Data Index: 1122801 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5269. Min Act: -0.0003

Data Index: 708656 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4976. Min Act: -0.0003

Data Index: 163830 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4901. Min Act: -0.0003

Data Index: 1253996 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4985. Min Act: -0.0003

Data Index: 813551 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5094. Min Act: -0.0003

Data Index: 1304888 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5095. Min Act: -0.0003

Data Index: 180717 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4778. Min Act: -0.0003

Data Index: 927714 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5109. Min Act: -0.0003

Data Index: 942543 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4917. Min Act: -0.0003

Data Index: 104561 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4875. Min Act: -0.0003

Data Index: 265830 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4796. Min Act: -0.0003

Data Index: 89604 (C4 (Web Text))

Max Activating Token Index: 293