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

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

Neuron 1413 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: 0.9452. Min Range: -0.9452

Max Act: 0.9452. Min Act: -0.0001

Data Index: 898716 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8328. Min Act: -0.0000

Data Index: 602913 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7751. Min Act: -0.0001

Data Index: 97091 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7678. Min Act: -0.0000

Data Index: 384547 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7173. Min Act: -0.0001

Data Index: 66495 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7231. Min Act: -0.0001

Data Index: 172604 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7002. Min Act: -0.0000

Data Index: 466487 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6794. Min Act: -0.0000

Data Index: 417690 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6715. Min Act: -0.0000

Data Index: 174118 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6844. Min Act: -0.0001

Data Index: 1295041 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6801. Min Act: -0.0000

Data Index: 596707 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6549. Min Act: -0.0000

Data Index: 703235 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5876. Min Act: -0.0000

Data Index: 588284 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6400. Min Act: -0.0000

Data Index: 123259 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6515. Min Act: -0.0001

Data Index: 1011777 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6530. Min Act: -0.0001

Data Index: 448445 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6258. Min Act: -0.0000

Data Index: 517796 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6255. Min Act: -0.0000

Data Index: 680237 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6061. Min Act: -0.0000

Data Index: 816449 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6199. Min Act: -0.0001

Data Index: 817165 (C4 (Web Text))

Max Activating Token Index: 927