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

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

Neuron 644 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: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0003

Data Index: 36945 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0003

Data Index: 21500 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0589. Min Act: -0.0003

Data Index: 984436 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1101035 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0562. Min Act: -0.0002

Data Index: 162416 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1252926 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0556. Min Act: -0.0003

Data Index: 188133 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0556. Min Act: -0.0003

Data Index: 42979 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1101212 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0542. Min Act: -0.0003

Data Index: 129336 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0535. Min Act: -0.0003

Data Index: 958114 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0515. Min Act: -0.0003

Data Index: 59829 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0472. Min Act: -0.0003

Data Index: 58675 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1143727 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0519. Min Act: -0.0003

Data Index: 259386 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1276230 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0501. Min Act: -0.0003

Data Index: 843969 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0500. Min Act: -0.0003

Data Index: 338486 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0499. Min Act: -0.0003

Data Index: 881188 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0507. Min Act: -0.0003

Data Index: 33747 (C4 (Web Text))

Max Activating Token Index: 96