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

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

Neuron 1481 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.2956. Min Act: -0.0000

Data Index: 1531865 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.1609. Min Act: -0.0000

Data Index: 1412841 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.0606. Min Act: -0.0000

Data Index: 1603664 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1381027 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.1825. Min Act: -0.0000

Data Index: 1491434 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9868. Min Act: -0.0000

Data Index: 1454061 (Python Code)

Max Activating Token Index: 341

Text #6

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1508578 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.0531. Min Act: -0.0000

Data Index: 1532882 (Python Code)

Max Activating Token Index: 66

Text #8

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9618. Min Act: -0.0000

Data Index: 1621865 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.8303. Min Act: -0.0000

Data Index: 1548594 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1489270 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.8005. Min Act: -0.0000

Data Index: 1414980 (Python Code)

Max Activating Token Index: 181

Text #12

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1556599 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7695. Min Act: -0.0000

Data Index: 1526564 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.8492. Min Act: -0.0000

Data Index: 1585869 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1482737 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1501905 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7672. Min Act: -0.0000

Data Index: 1449570 (Python Code)

Max Activating Token Index: 137

Text #18

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.6077. Min Act: -0.0000

Data Index: 1462815 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1479103 (Python Code)

Max Activating Token Index: 161