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

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

Neuron 1874 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: 0.6115. Min Range: -0.6115

Max Act: 0.6115. Min Act: -0.0000

Data Index: 256267 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4471. Min Act: -0.0000

Data Index: 325587 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4732. Min Act: -0.0001

Data Index: 878678 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4517. Min Act: -0.0001

Data Index: 60279 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1403558 (Python Code)

Max Activating Token Index: 649

Text #5

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1006011 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1532524 (Python Code)

Max Activating Token Index: 158

Text #7

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4345. Min Act: -0.0001

Data Index: 861830 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4296. Min Act: -0.0001

Data Index: 585449 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4092. Min Act: -0.0001

Data Index: 998137 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3947. Min Act: -0.0001

Data Index: 1260323 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.4187. Min Act: -0.0001

Data Index: 234120 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3783. Min Act: -0.0001

Data Index: 163026 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3825. Min Act: -0.0000

Data Index: 4354 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3829. Min Act: -0.0000

Data Index: 624727 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3785. Min Act: -0.0001

Data Index: 887364 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3757. Min Act: -0.0000

Data Index: 132543 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1439081 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3732. Min Act: -0.0001

Data Index: 617838 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.6115. Min Range: -0.6115

Max Act: 0.3508. Min Act: -0.0000

Data Index: 456567 (C4 (Web Text))

Max Activating Token Index: 556