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

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

Neuron 238 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.8827. Min Act: -0.0001

Data Index: 1003624 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.8473. Min Act: -0.0001

Data Index: 480 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6768. Min Act: -0.0001

Data Index: 107612 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.8283. Min Act: -0.0001

Data Index: 520747 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7842. Min Act: -0.0001

Data Index: 152239 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6711. Min Act: -0.0001

Data Index: 511333 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7668. Min Act: -0.0001

Data Index: 1016879 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7106. Min Act: -0.0001

Data Index: 701789 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7696. Min Act: -0.0001

Data Index: 483632 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7256. Min Act: -0.0001

Data Index: 767754 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6856. Min Act: -0.0001

Data Index: 387735 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7509. Min Act: -0.0001

Data Index: 714100 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7654. Min Act: -0.0001

Data Index: 486090 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.8075. Min Act: -0.0001

Data Index: 426635 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7497. Min Act: -0.0001

Data Index: 648764 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6601. Min Act: -0.0001

Data Index: 702484 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7067. Min Act: -0.0001

Data Index: 931141 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7099. Min Act: -0.0001

Data Index: 340178 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7004. Min Act: -0.0001

Data Index: 409943 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7180. Min Act: -0.0001

Data Index: 701010 (C4 (Web Text))

Max Activating Token Index: 131