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

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

Neuron 3726 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: 0.6637. Min Range: -0.6637

Max Act: 0.6216. Min Act: -0.0000

Data Index: 678507 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6320. Min Act: -0.0000

Data Index: 7403 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6043. Min Act: -0.0000

Data Index: 879674 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6637. Min Act: -0.0000

Data Index: 376780 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6206. Min Act: -0.0000

Data Index: 424927 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5109. Min Act: -0.0001

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1127864 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1244410 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5422. Min Act: -0.0000

Data Index: 327927 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5258. Min Act: -0.0000

Data Index: 858191 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5204. Min Act: -0.0000

Data Index: 963127 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5877. Min Act: -0.0000

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5357. Min Act: -0.0000

Data Index: 928599 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4995. Min Act: -0.0000

Data Index: 356709 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5287. Min Act: -0.0000

Data Index: 532040 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4927. Min Act: -0.0000

Data Index: 708730 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5306. Min Act: -0.0000

Data Index: 722308 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4899. Min Act: -0.0001

Data Index: 78024 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1319004 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4821. Min Act: -0.0000

Data Index: 986962 (C4 (Web Text))

Max Activating Token Index: 806