Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3991 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3978. Min Act: -0.0001

Data Index: 1480524 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2709. Min Act: -0.0001

Data Index: 1510204 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2688. Min Act: -0.0001

Data Index: 1608756 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1240. Min Act: -0.0001

Data Index: 1619789 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0430. Min Act: -0.0001

Data Index: 1330673 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9529. Min Act: -0.0001

Data Index: 1376720 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0566. Min Act: -0.0001

Data Index: 1366776 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0639. Min Act: -0.0001

Data Index: 1372845 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1389546 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0770. Min Act: -0.0001

Data Index: 1498893 (Python Code)

Max Activating Token Index: 766

Text #10

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0073. Min Act: -0.0001

Data Index: 1580945 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1434811 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8562. Min Act: -0.0001

Data Index: 138737 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1458022 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1438235 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1417017 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.7833. Min Act: -0.0001

Data Index: 1437457 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8593. Min Act: -0.0001

Data Index: 1610738 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1377547 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1387947 (Python Code)

Max Activating Token Index: 950