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

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

Neuron 1696 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: 2.9452. Min Range: -2.9452

Max Act: 2.9452. Min Act: -0.0000

Data Index: 556190 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.4755. Min Act: -0.0000

Data Index: 782668 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.6497. Min Act: -0.0000

Data Index: 479686 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.3581. Min Act: -0.0000

Data Index: 902652 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.5153. Min Act: -0.0000

Data Index: 1088566 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.4529. Min Act: -0.0000

Data Index: 315637 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.3305. Min Act: -0.0000

Data Index: 273411 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1075197 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.1643. Min Act: -0.0000

Data Index: 47006 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.1813. Min Act: -0.0000

Data Index: 325463 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.4010. Min Act: -0.0000

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.3839. Min Act: -0.0000

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.2465. Min Act: -0.0000

Data Index: 586426 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.2240. Min Act: -0.0000

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.2033. Min Act: -0.0000

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.3069. Min Act: -0.0000

Data Index: 283485 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.1881. Min Act: -0.0000

Data Index: 576746 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.0884. Min Act: -0.0000

Data Index: 134967 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.0742. Min Act: -0.0000

Data Index: 606478 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 2.9452. Min Range: -2.9452

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1067406 (C4 (Web Text))

Max Activating Token Index: 378