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

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

Neuron 5883 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.4248. Min Act: -0.0000

Data Index: 152192 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.2408. Min Act: -0.0000

Data Index: 68288 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.1460. Min Act: -0.0000

Data Index: 93141 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1229064 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1538507 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0897. Min Act: -0.0000

Data Index: 528903 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0376. Min Act: -0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0449. Min Act: -0.0000

Data Index: 866547 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1187151 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.1149. Min Act: -0.0000

Data Index: 979433 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0379. Min Act: -0.0000

Data Index: 502697 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0624. Min Act: -0.0000

Data Index: 675854 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9826. Min Act: -0.0000

Data Index: 81555 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1370364 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9843. Min Act: -0.0000

Data Index: 97170 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9865. Min Act: -0.0000

Data Index: 887936 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1402406 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1496427 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.8851. Min Act: -0.0000

Data Index: 972922 (C4 (Web Text))

Max Activating Token Index: 933