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

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

Neuron 5638 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: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 905094 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1416865 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1584071 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1428478 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1366776 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1572656 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1453734 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1594404 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1033726 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1508029 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1418804 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1517983 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1575634 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1511841 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1583445 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1426526 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1487678 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1473290 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1385971 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1618548 (Python Code)

Max Activating Token Index: 10