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

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

Neuron 1045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.8835. Min Act: -0.0000

Data Index: 1398527 (Python Code)

Max Activating Token Index: 619

Text #1

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.5267. Min Act: -0.0000

Data Index: 1446379 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.2275. Min Act: -0.0000

Data Index: 1630222 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.1391. Min Act: -0.0000

Data Index: 1364076 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.2457. Min Act: -0.0000

Data Index: 1417950 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.3389. Min Act: -0.0000

Data Index: 1444257 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.4354. Min Act: -0.0000

Data Index: 1518750 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1450738 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.2475. Min Act: -0.0000

Data Index: 1417814 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.2499. Min Act: -0.0000

Data Index: 1624274 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.2268. Min Act: -0.0000

Data Index: 1633907 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 3.8835. Min Range: -3.8835

Max Act: 2.9398. Min Act: -0.0000

Data Index: 1541592 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.1309. Min Act: -0.0000

Data Index: 1364098 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 3.8835. Min Range: -3.8835

Max Act: 2.9685. Min Act: -0.0000

Data Index: 1457619 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.0986. Min Act: -0.0000

Data Index: 1426884 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 3.8835. Min Range: -3.8835

Max Act: 2.9343. Min Act: -0.0000

Data Index: 1508635 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 3.8835. Min Range: -3.8835

Max Act: 2.9122. Min Act: -0.0000

Data Index: 1440859 (Python Code)

Max Activating Token Index: 226

Text #17

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.0215. Min Act: -0.0000

Data Index: 1618242 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.0005. Min Act: -0.0000

Data Index: 1377328 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 3.8835. Min Range: -3.8835

Max Act: 2.8711. Min Act: -0.0000

Data Index: 1466235 (Python Code)

Max Activating Token Index: 843