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

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

Neuron 4478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1642. Min Range: -4.1642

Max Act: 4.1642. Min Act: -0.0000

Data Index: 864095 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 4.1642. Min Range: -4.1642

Max Act: 4.0738. Min Act: -0.0000

Data Index: 1319621 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.9297. Min Act: -0.0000

Data Index: 996536 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.7391. Min Act: -0.0000

Data Index: 531207 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 4.1642. Min Range: -4.1642

Max Act: 4.0561. Min Act: -0.0000

Data Index: 678674 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 4.1642. Min Range: -4.1642

Max Act: 4.0289. Min Act: -0.0000

Data Index: 692503 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.6470. Min Act: -0.0000

Data Index: 353118 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.7909. Min Act: -0.0000

Data Index: 466880 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.3053. Min Act: -0.0000

Data Index: 547533 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.3026. Min Act: -0.0000

Data Index: 722926 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.3400. Min Act: -0.0000

Data Index: 956933 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.4326. Min Act: -0.0000

Data Index: 310684 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.4403. Min Act: -0.0000

Data Index: 926235 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.3346. Min Act: -0.0000

Data Index: 1187410 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.0217. Min Act: -0.0000

Data Index: 670226 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.0775. Min Act: -0.0000

Data Index: 161732 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.0502. Min Act: -0.0000

Data Index: 1061590 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 4.1642. Min Range: -4.1642

Max Act: 3.0331. Min Act: -0.0000

Data Index: 878187 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 4.1642. Min Range: -4.1642

Max Act: 2.8068. Min Act: -0.0000

Data Index: 1057181 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 4.1642. Min Range: -4.1642

Max Act: 2.7332. Min Act: -0.0000

Data Index: 553682 (C4 (Web Text))

Max Activating Token Index: 89