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

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

Neuron 636 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: 3.4307. Min Range: -3.4307

Max Act: 3.4307. Min Act: -0.0001

Data Index: 1435906 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3337. Min Act: -0.0001

Data Index: 1577000 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.8866. Min Act: -0.0001

Data Index: 1451113 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.1289. Min Act: -0.0000

Data Index: 1572043 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.9996. Min Act: -0.0001

Data Index: 1431296 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.1533. Min Act: -0.0000

Data Index: 1499352 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.9650. Min Act: -0.0001

Data Index: 1501496 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.0482. Min Act: -0.0000

Data Index: 1640931 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.0833. Min Act: -0.0001

Data Index: 1487091 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.8054. Min Act: -0.0000

Data Index: 1378686 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.0733. Min Act: -0.0000

Data Index: 1413425 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.9221. Min Act: -0.0001

Data Index: 1627683 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.9065. Min Act: -0.0001

Data Index: 1480964 (Python Code)

Max Activating Token Index: 755

Text #13

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.8596. Min Act: -0.0000

Data Index: 1620724 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.0356. Min Act: -0.0001

Data Index: 1474983 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.8705. Min Act: -0.0001

Data Index: 1607867 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.8841. Min Act: -0.0000

Data Index: 1477811 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.7209. Min Act: -0.0001

Data Index: 1498260 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.8472. Min Act: -0.0001

Data Index: 1486894 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 3.4307. Min Range: -3.4307

Max Act: 2.7155. Min Act: -0.0000

Data Index: 1367180 (Python Code)

Max Activating Token Index: 47