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

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

Neuron 4735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0505. Min Range: -2.0505

Max Act: 2.0185. Min Act: -0.0000

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.8719. Min Act: -0.0000

Data Index: 575146 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.9015. Min Act: -0.0000

Data Index: 389655 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 2.0505. Min Range: -2.0505

Max Act: 2.0505. Min Act: -0.0000

Data Index: 123781 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.7197. Min Act: -0.0000

Data Index: 177623 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.8885. Min Act: -0.0000

Data Index: 321562 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.7793. Min Act: -0.0000

Data Index: 613795 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1129761 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.6774. Min Act: -0.0000

Data Index: 798799 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.4340. Min Act: -0.0000

Data Index: 507618 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.5361. Min Act: -0.0000

Data Index: 204680 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.5090. Min Act: -0.0000

Data Index: 674248 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1144179 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.4944. Min Act: -0.0000

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.4825. Min Act: -0.0000

Data Index: 572791 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.3546. Min Act: -0.0000

Data Index: 580116 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.4620. Min Act: -0.0000

Data Index: 497054 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.5380. Min Act: -0.0000

Data Index: 208334 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1250938 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.0505. Min Range: -2.0505

Max Act: 1.3490. Min Act: -0.0000

Data Index: 881252 (C4 (Web Text))

Max Activating Token Index: 825