Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3850. Min Act: -0.0000

Data Index: 526157 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3572. Min Act: 0.0000

Data Index: 989423 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1089733 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3022. Min Act: -0.0000

Data Index: 347881 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3001. Min Act: 0.0001

Data Index: 716314 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2855. Min Act: -0.0000

Data Index: 133508 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2854. Min Act: -0.0000

Data Index: 533677 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2705. Min Act: -0.0000

Data Index: 535826 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2682. Min Act: 0.0001

Data Index: 586366 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2717. Min Act: 0.0000

Data Index: 435973 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2622. Min Act: -0.0000

Data Index: 565383 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2709. Min Act: -0.0000

Data Index: 95610 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2606. Min Act: -0.0000

Data Index: 441264 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2596. Min Act: 0.0001

Data Index: 1044163 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2555. Min Act: -0.0000

Data Index: 401052 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2417. Min Act: -0.0000

Data Index: 892 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2563. Min Act: -0.0000

Data Index: 914980 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2492. Min Act: -0.0000

Data Index: 448843 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2493. Min Act: 0.0000

Data Index: 175567 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1231286 (C4 (Web Text))

Max Activating Token Index: 163