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

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

Neuron 2352 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2826. Min Range: -5.2826

Max Act: 5.2826. Min Act: -0.0000

Data Index: 1396887 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.6157. Min Act: -0.0000

Data Index: 1426887 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.3842. Min Act: -0.0000

Data Index: 1437973 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.3823. Min Act: -0.0000

Data Index: 1618056 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.2278. Min Act: -0.0000

Data Index: 1465769 (Python Code)

Max Activating Token Index: 831

Text #5

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.2419. Min Act: -0.0000

Data Index: 1572765 (Python Code)

Max Activating Token Index: 570

Text #6

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.2514. Min Act: -0.0000

Data Index: 1424409 (Python Code)

Max Activating Token Index: 320

Text #7

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.2181. Min Act: -0.0000

Data Index: 1543101 (Python Code)

Max Activating Token Index: 588

Text #8

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.1891. Min Act: -0.0000

Data Index: 1648541 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.0261. Min Act: -0.0000

Data Index: 1470914 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.1658. Min Act: -0.0000

Data Index: 1363831 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.3092. Min Act: -0.0000

Data Index: 1607217 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.1531. Min Act: -0.0000

Data Index: 1455919 (Python Code)

Max Activating Token Index: 409

Text #13

Max Range: 5.2826. Min Range: -5.2826

Max Act: 2.9448. Min Act: -0.0000

Data Index: 1426863 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.2013. Min Act: -0.0000

Data Index: 1456148 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.1844. Min Act: -0.0000

Data Index: 1483688 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 5.2826. Min Range: -5.2826

Max Act: 3.0244. Min Act: -0.0000

Data Index: 1385560 (Python Code)

Max Activating Token Index: 266

Text #17

Max Range: 5.2826. Min Range: -5.2826

Max Act: 2.8468. Min Act: -0.0000

Data Index: 1597738 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 5.2826. Min Range: -5.2826

Max Act: 2.9800. Min Act: -0.0000

Data Index: 1375872 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 5.2826. Min Range: -5.2826

Max Act: 2.9813. Min Act: -0.0000

Data Index: 1439834 (Python Code)

Max Activating Token Index: 131