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

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

Neuron 4285 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8813. Min Range: -1.8813

Max Act: 1.8813. Min Act: -0.0000

Data Index: 1424605 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 1.8813. Min Range: -1.8813

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1567816 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 1.8813. Min Range: -1.8813

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1596463 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 1.8813. Min Range: -1.8813

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1459544 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1504806 (Python Code)

Max Activating Token Index: 720

Text #5

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1555942 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1554415 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1603597 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1362490 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1611771 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1608382 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1444113 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1370871 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1482093 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1382072 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1524542 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1563298 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1421059 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1502012 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 1.8813. Min Range: -1.8813

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1486585 (Python Code)

Max Activating Token Index: 569