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

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

Neuron 911 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1623132 (Python Code)

Max Activating Token Index: 571

Text #1

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.7521. Min Act: -0.0000

Data Index: 1616198 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.7373. Min Act: -0.0000

Data Index: 1550186 (Python Code)

Max Activating Token Index: 849

Text #3

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.8392. Min Act: -0.0000

Data Index: 1424789 (Python Code)

Max Activating Token Index: 606

Text #4

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.5848. Min Act: -0.0000

Data Index: 1464456 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.8980. Min Act: -0.0000

Data Index: 1543862 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.6309. Min Act: -0.0000

Data Index: 1632156 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.7316. Min Act: -0.0000

Data Index: 1454327 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.6800. Min Act: -0.0000

Data Index: 1369412 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.6184. Min Act: -0.0000

Data Index: 1571489 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.4615. Min Act: -0.0000

Data Index: 1482953 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.6221. Min Act: -0.0000

Data Index: 1544476 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.7337. Min Act: -0.0000

Data Index: 1386240 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.4990. Min Act: -0.0000

Data Index: 1480951 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.5954. Min Act: -0.0000

Data Index: 1364149 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.4877. Min Act: -0.0000

Data Index: 1644558 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.6957. Min Act: -0.0001

Data Index: 1373409 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.5840. Min Act: -0.0001

Data Index: 1373429 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.7084. Min Act: -0.0000

Data Index: 1581834 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 2.9781. Min Range: -2.9781

Max Act: 2.5508. Min Act: -0.0001

Data Index: 1563177 (Python Code)

Max Activating Token Index: 191