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

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

Neuron 1249 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1557708 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.2746. Min Act: 0.0001

Data Index: 1394151 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1361236 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.2420. Min Act: 0.0000

Data Index: 1465123 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1458749 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1656329 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1531536 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1632153 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1415369 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.0190. Min Act: 0.0000

Data Index: 1618791 (Python Code)

Max Activating Token Index: 720

Text #10

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1627626 (Python Code)

Max Activating Token Index: 303

Text #11

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1531441 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1439620 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1426569 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1430766 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.8233. Min Act: 0.0001

Data Index: 1536390 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1448471 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1412200 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1633862 (Python Code)

Max Activating Token Index: 777

Text #19

Max Range: 1.6674. Min Range: -1.6674

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1374264 (Python Code)

Max Activating Token Index: 950