Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1878 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1067727 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.7320. Min Act: -0.0001

Data Index: 700490 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6597. Min Act: -0.0001

Data Index: 664966 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6751. Min Act: -0.0001

Data Index: 420631 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6287. Min Act: -0.0000

Data Index: 373978 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6214. Min Act: -0.0000

Data Index: 298434 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5800. Min Act: -0.0001

Data Index: 215298 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5864. Min Act: -0.0001

Data Index: 276797 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1275369 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5623. Min Act: -0.0000

Data Index: 590368 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6100. Min Act: -0.0001

Data Index: 556259 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6074. Min Act: -0.0001

Data Index: 902698 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5970. Min Act: -0.0001

Data Index: 719737 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1308070 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5996. Min Act: -0.0001

Data Index: 746219 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6735. Min Act: -0.0001

Data Index: 280828 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5812. Min Act: -0.0001

Data Index: 158189 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5380. Min Act: -0.0001

Data Index: 167168 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5536. Min Act: -0.0001

Data Index: 77068 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6441. Min Act: -0.0001

Data Index: 771868 (C4 (Web Text))

Max Activating Token Index: 920