Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 227 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.9252. Min Act: -0.0000

Data Index: 595574 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.5800. Min Act: -0.0000

Data Index: 103352 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.6403. Min Act: -0.0000

Data Index: 620398 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.5427. Min Act: -0.0000

Data Index: 191903 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.1038. Min Act: -0.0000

Data Index: 840027 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.3577. Min Act: -0.0000

Data Index: 873828 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.1785. Min Act: -0.0000

Data Index: 688243 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.1460. Min Act: -0.0000

Data Index: 114683 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.0567. Min Act: -0.0000

Data Index: 817337 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.8353. Min Act: -0.0000

Data Index: 8299 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.9902. Min Act: -0.0000

Data Index: 1041081 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7970. Min Act: -0.0000

Data Index: 664951 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.2643. Min Act: -0.0000

Data Index: 309314 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7893. Min Act: -0.0000

Data Index: 995925 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.9252. Min Range: -3.9252

Max Act: 3.0378. Min Act: -0.0000

Data Index: 966183 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7371. Min Act: -0.0000

Data Index: 942005 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7336. Min Act: -0.0000

Data Index: 1055491 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7043. Min Act: -0.0000

Data Index: 262012 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7918. Min Act: -0.0000

Data Index: 710247 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 3.9252. Min Range: -3.9252

Max Act: 2.7909. Min Act: -0.0000

Data Index: 1284241 (C4 (Web Text))

Max Activating Token Index: 77