Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1990 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9368. Min Range: -2.9368

Max Act: 2.9368. Min Act: 0.0000

Data Index: 1375921 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 2.9368. Min Range: -2.9368

Max Act: 2.2263. Min Act: -0.0000

Data Index: 1459491 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 2.9368. Min Range: -2.9368

Max Act: 2.0723. Min Act: -0.0000

Data Index: 1460508 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.8900. Min Act: -0.0000

Data Index: 1563165 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.8057. Min Act: -0.0000

Data Index: 1643062 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.7557. Min Act: -0.0000

Data Index: 1402623 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.6554. Min Act: -0.0000

Data Index: 1565187 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.7383. Min Act: -0.0000

Data Index: 1582509 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5837. Min Act: -0.0000

Data Index: 1534552 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1567497 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.6592. Min Act: -0.0000

Data Index: 1539979 (Python Code)

Max Activating Token Index: 616

Text #11

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.6631. Min Act: 0.0000

Data Index: 1501224 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.7180. Min Act: -0.0000

Data Index: 1516496 (Python Code)

Max Activating Token Index: 611

Text #13

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1606550 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.6084. Min Act: -0.0000

Data Index: 555257 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5855. Min Act: -0.0000

Data Index: 1611329 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5893. Min Act: -0.0000

Data Index: 1414913 (Python Code)

Max Activating Token Index: 490

Text #17

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5333. Min Act: -0.0000

Data Index: 809151 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5009. Min Act: -0.0000

Data Index: 1466578 (Python Code)

Max Activating Token Index: 377

Text #19

Max Range: 2.9368. Min Range: -2.9368

Max Act: 1.5774. Min Act: -0.0000

Data Index: 1570230 (Python Code)

Max Activating Token Index: 395