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

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

Neuron 294 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.4189. Min Act: -0.0000

Data Index: 1509569 (Python Code)

Max Activating Token Index: 921

Text #1

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.3374. Min Act: -0.0000

Data Index: 1400667 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.2826. Min Act: -0.0000

Data Index: 1494782 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.2088. Min Act: -0.0000

Data Index: 1511165 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.5340. Min Act: -0.0000

Data Index: 1499903 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.3377. Min Act: -0.0000

Data Index: 1366739 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.1101. Min Act: -0.0000

Data Index: 1593591 (Python Code)

Max Activating Token Index: 341

Text #7

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.2475. Min Act: -0.0000

Data Index: 1387432 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.2169. Min Act: -0.0000

Data Index: 1475098 (Python Code)

Max Activating Token Index: 824

Text #9

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.2015. Min Act: -0.0000

Data Index: 1456145 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.0141. Min Act: -0.0000

Data Index: 1565673 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.1192. Min Act: -0.0000

Data Index: 1438513 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 4.5340. Min Range: -4.5340

Max Act: 3.9713. Min Act: -0.0000

Data Index: 1444834 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.2649. Min Act: -0.0000

Data Index: 1607555 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 4.5340. Min Range: -4.5340

Max Act: 3.9438. Min Act: -0.0000

Data Index: 1536593 (Python Code)

Max Activating Token Index: 723

Text #15

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.0684. Min Act: -0.0000

Data Index: 1464189 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 4.5340. Min Range: -4.5340

Max Act: 4.1943. Min Act: -0.0000

Data Index: 1442528 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 4.5340. Min Range: -4.5340

Max Act: 3.8403. Min Act: -0.0000

Data Index: 1496463 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 4.5340. Min Range: -4.5340

Max Act: 3.9779. Min Act: -0.0000

Data Index: 1543618 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 4.5340. Min Range: -4.5340

Max Act: 3.9852. Min Act: -0.0000

Data Index: 1442908 (Python Code)

Max Activating Token Index: 180