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

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

Neuron 2813 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7248. Min Range: -3.7248

Max Act: 3.7248. Min Act: -0.0000

Data Index: 1439474 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 3.7248. Min Range: -3.7248

Max Act: 3.7047. Min Act: -0.0000

Data Index: 1449117 (Python Code)

Max Activating Token Index: 406

Text #2

Max Range: 3.7248. Min Range: -3.7248

Max Act: 3.2518. Min Act: -0.0000

Data Index: 1494704 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 3.7248. Min Range: -3.7248

Max Act: 3.1844. Min Act: -0.0000

Data Index: 1651689 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 3.7248. Min Range: -3.7248

Max Act: 3.0203. Min Act: -0.0000

Data Index: 1501036 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.9361. Min Act: -0.0000

Data Index: 1365986 (Python Code)

Max Activating Token Index: 533

Text #6

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.9194. Min Act: -0.0000

Data Index: 1588469 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.4478. Min Act: -0.0000

Data Index: 1648666 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.8573. Min Act: -0.0000

Data Index: 1398665 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.5760. Min Act: -0.0000

Data Index: 1412213 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.6949. Min Act: -0.0000

Data Index: 1612541 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.1592. Min Act: -0.0000

Data Index: 1404854 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1578785 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.6584. Min Act: -0.0000

Data Index: 1383458 (Python Code)

Max Activating Token Index: 459

Text #14

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.7409. Min Act: -0.0000

Data Index: 1648748 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.7253. Min Act: -0.0000

Data Index: 1416395 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.8619. Min Act: -0.0000

Data Index: 1362611 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.4061. Min Act: -0.0000

Data Index: 1600788 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.6523. Min Act: -0.0000

Data Index: 1602314 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 3.7248. Min Range: -3.7248

Max Act: 2.5200. Min Act: -0.0000

Data Index: 1652083 (Python Code)

Max Activating Token Index: 847