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

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

Neuron 3468 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: 1.5676. Min Range: -1.5676

Max Act: 1.5676. Min Act: -0.0001

Data Index: 1619979 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.3977. Min Act: -0.0001

Data Index: 1539751 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.3950. Min Act: -0.0001

Data Index: 1572835 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.4114. Min Act: -0.0001

Data Index: 1606106 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.4114. Min Act: -0.0001

Data Index: 1526783 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.4046. Min Act: -0.0001

Data Index: 1626958 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2080. Min Act: -0.0001

Data Index: 1479319 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.3703. Min Act: -0.0001

Data Index: 1652506 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2638. Min Act: -0.0001

Data Index: 1551616 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2115. Min Act: -0.0001

Data Index: 1399576 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2405. Min Act: -0.0001

Data Index: 1450559 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2405. Min Act: -0.0001

Data Index: 1572786 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2716. Min Act: -0.0001

Data Index: 1627084 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2629. Min Act: -0.0001

Data Index: 1532549 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2747. Min Act: -0.0001

Data Index: 1412168 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2091. Min Act: -0.0001

Data Index: 1431718 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2251. Min Act: -0.0001

Data Index: 1592319 (Python Code)

Max Activating Token Index: 393

Text #17

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.1955. Min Act: -0.0001

Data Index: 1639529 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.2562. Min Act: -0.0001

Data Index: 1612885 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 1.5676. Min Range: -1.5676

Max Act: 1.1604. Min Act: -0.0001

Data Index: 1476310 (Python Code)

Max Activating Token Index: 440