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

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

Neuron 3654 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: 0.5481. Min Range: -0.5481

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1563034 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1605866 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1445649 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5116. Min Act: -0.0001

Data Index: 1614718 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1617136 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1457147 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1491374 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1427995 (Python Code)

Max Activating Token Index: 122

Text #8

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1588764 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1517228 (Python Code)

Max Activating Token Index: 712

Text #10

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1367277 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1648453 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1606042 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1398240 (Python Code)

Max Activating Token Index: 183

Text #14

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1506966 (Python Code)

Max Activating Token Index: 407

Text #15

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1456439 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1410940 (Python Code)

Max Activating Token Index: 594

Text #17

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1463528 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1473980 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1402312 (Python Code)

Max Activating Token Index: 691