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

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

Neuron 2426 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3908. Min Act: -0.0000

Data Index: 1381701 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2611. Min Act: -0.0000

Data Index: 1535774 (Python Code)

Max Activating Token Index: 702

Text #2

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.1727. Min Act: -0.0000

Data Index: 1541272 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.8300. Min Act: -0.0000

Data Index: 1360040 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2196. Min Act: -0.0000

Data Index: 1591935 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.8636. Min Act: -0.0000

Data Index: 1465088 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.8449. Min Act: -0.0000

Data Index: 1515388 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.8381. Min Act: -0.0000

Data Index: 1475514 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.6426. Min Act: -0.0000

Data Index: 1651504 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.9371. Min Act: -0.0001

Data Index: 1500632 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.7685. Min Act: -0.0000

Data Index: 1583073 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.9361. Min Act: -0.0000

Data Index: 1616134 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.9765. Min Act: -0.0000

Data Index: 1507745 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.5427. Min Act: -0.0000

Data Index: 1554393 (Python Code)

Max Activating Token Index: 150

Text #14

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.7014. Min Act: -0.0000

Data Index: 1441208 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.7289. Min Act: -0.0000

Data Index: 1432617 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.5461. Min Act: -0.0000

Data Index: 1524464 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.6672. Min Act: -0.0000

Data Index: 1397368 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1452781 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 3.3908. Min Range: -3.3908

Max Act: 2.7245. Min Act: -0.0001

Data Index: 1504053 (Python Code)

Max Activating Token Index: 599