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

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

Neuron 4714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4762. Min Act: -0.0002

Data Index: 1384808 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.5221. Min Act: -0.0002

Data Index: 1521235 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.4244. Min Act: -0.0002

Data Index: 1572799 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3713. Min Act: -0.0002

Data Index: 1546077 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3551. Min Act: -0.0002

Data Index: 1565055 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3608. Min Act: -0.0002

Data Index: 1433951 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3560. Min Act: -0.0002

Data Index: 1505625 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3512. Min Act: -0.0002

Data Index: 1590996 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3172. Min Act: -0.0002

Data Index: 1432221 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3135. Min Act: -0.0002

Data Index: 1385034 (Python Code)

Max Activating Token Index: 105

Text #10

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2960. Min Act: -0.0002

Data Index: 1381743 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.3038. Min Act: -0.0002

Data Index: 1378226 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2581. Min Act: -0.0002

Data Index: 1639828 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2362. Min Act: -0.0002

Data Index: 1369957 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2399. Min Act: -0.0002

Data Index: 1497440 (Python Code)

Max Activating Token Index: 529

Text #15

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2492. Min Act: -0.0002

Data Index: 1396066 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2597. Min Act: -0.0002

Data Index: 1565857 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2439. Min Act: -0.0002

Data Index: 1481476 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2410. Min Act: -0.0002

Data Index: 1649621 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 0.5221. Min Range: -0.5221

Max Act: 0.2397. Min Act: -0.0002

Data Index: 1516346 (Python Code)

Max Activating Token Index: 40