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

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

Neuron 2457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1783. Min Range: -2.1783

Max Act: 2.1783. Min Act: -0.0000

Data Index: 1140615 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.8347. Min Act: -0.0000

Data Index: 401783 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 2.1783. Min Range: -2.1783

Max Act: 2.0072. Min Act: -0.0000

Data Index: 149501 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.8335. Min Act: -0.0000

Data Index: 1341601 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.7251. Min Act: -0.0000

Data Index: 51098 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5626. Min Act: -0.0000

Data Index: 463732 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.6415. Min Act: -0.0000

Data Index: 973262 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.6300. Min Act: -0.0000

Data Index: 90462 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5392. Min Act: -0.0000

Data Index: 1193494 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5052. Min Act: -0.0000

Data Index: 731817 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5094. Min Act: -0.0000

Data Index: 315587 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5621. Min Act: -0.0000

Data Index: 548792 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1187118 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5044. Min Act: -0.0000

Data Index: 498760 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5946. Min Act: -0.0000

Data Index: 221585 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5809. Min Act: -0.0000

Data Index: 290570 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1200298 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.3792. Min Act: -0.0000

Data Index: 990631 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.5545. Min Act: -0.0000

Data Index: 348014 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 2.1783. Min Range: -2.1783

Max Act: 1.3704. Min Act: -0.0000

Data Index: 61688 (C4 (Web Text))

Max Activating Token Index: 696