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

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

Neuron 5450 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0001

Data Index: 60283 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0590. Min Act: -0.0001

Data Index: 735293 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0619. Min Act: -0.0001

Data Index: 132637 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0617. Min Act: -0.0001

Data Index: 438581 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0534. Min Act: -0.0001

Data Index: 835324 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0573. Min Act: -0.0001

Data Index: 21920 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0555. Min Act: -0.0001

Data Index: 129295 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1112943 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0511. Min Act: -0.0001

Data Index: 952234 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0526. Min Act: -0.0001

Data Index: 573533 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1022577 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0482. Min Act: -0.0001

Data Index: 672656 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1208962 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0509. Min Act: -0.0001

Data Index: 524623 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1119125 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0480. Min Act: -0.0001

Data Index: 494853 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1313633 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1036860 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0475. Min Act: -0.0001

Data Index: 131284 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0476. Min Act: -0.0001

Data Index: 298801 (C4 (Web Text))

Max Activating Token Index: 807