Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2846 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2234. Min Act: -0.0001

Data Index: 1568371 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2701. Min Act: -0.0001

Data Index: 1640417 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2264. Min Act: -0.0001

Data Index: 1455927 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1715. Min Act: -0.0001

Data Index: 1409652 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0876. Min Act: -0.0001

Data Index: 1654044 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1533. Min Act: -0.0001

Data Index: 1622445 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1559. Min Act: -0.0001

Data Index: 1648561 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1199. Min Act: -0.0001

Data Index: 1507616 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1082. Min Act: -0.0001

Data Index: 1499877 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1005. Min Act: -0.0001

Data Index: 1645734 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0605. Min Act: -0.0001

Data Index: 1604715 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.1287. Min Act: -0.0001

Data Index: 1617901 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0912. Min Act: -0.0001

Data Index: 1384388 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0906. Min Act: -0.0001

Data Index: 1592737 (Python Code)

Max Activating Token Index: 335

Text #14

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0405. Min Act: -0.0001

Data Index: 1378481 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0691. Min Act: -0.0001

Data Index: 1496634 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0571. Min Act: -0.0001

Data Index: 1643052 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9841. Min Act: -0.0001

Data Index: 1548914 (Python Code)

Max Activating Token Index: 301

Text #18

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0782. Min Act: -0.0001

Data Index: 1449216 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0734. Min Act: -0.0001

Data Index: 1592542 (Python Code)

Max Activating Token Index: 157