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

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

Neuron 3991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.6746. Min Act: -0.0002

Data Index: 497272 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.7859. Min Act: -0.0002

Data Index: 933076 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.3246. Min Act: -0.0001

Data Index: 369536 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.3518. Min Act: -0.0001

Data Index: 1285493 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.2783. Min Act: -0.0001

Data Index: 503581 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.3438. Min Act: -0.0002

Data Index: 155662 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.2657. Min Act: -0.0001

Data Index: 1242802 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.2619. Min Act: -0.0002

Data Index: 613554 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.1631. Min Act: -0.0002

Data Index: 630156 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.2312. Min Act: -0.0001

Data Index: 160382 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.1583. Min Act: -0.0002

Data Index: 302578 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.0417. Min Act: -0.0002

Data Index: 309441 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.3293. Min Act: -0.0002

Data Index: 1203449 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.1846. Min Act: -0.0002

Data Index: 585058 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.1968. Min Act: -0.0002

Data Index: 112383 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.1944. Min Act: -0.0002

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.0739. Min Act: -0.0002

Data Index: 592463 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.0676. Min Act: -0.0002

Data Index: 425802 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.2055. Min Act: -0.0001

Data Index: 796150 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.7859. Min Range: -1.7859

Max Act: 1.0261. Min Act: -0.0002

Data Index: 251906 (C4 (Web Text))

Max Activating Token Index: 1018