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

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

Neuron 3821 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0980. Min Range: -1.0980

Max Act: 1.0980. Min Act: -0.0001

Data Index: 1417243 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.9613. Min Act: -0.0001

Data Index: 1569889 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.9057. Min Act: -0.0001

Data Index: 1628927 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8338. Min Act: -0.0001

Data Index: 1367573 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8797. Min Act: -0.0001

Data Index: 602658 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8355. Min Act: -0.0001

Data Index: 1616966 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1582983 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1614749 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8114. Min Act: -0.0001

Data Index: 1468885 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1581458 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7583. Min Act: -0.0001

Data Index: 1523372 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7932. Min Act: -0.0001

Data Index: 1485060 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7569. Min Act: -0.0001

Data Index: 1514875 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1597946 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1384530 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1600125 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7747. Min Act: -0.0001

Data Index: 1483377 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1361187 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7630. Min Act: -0.0001

Data Index: 1510235 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7574. Min Act: -0.0001

Data Index: 1597562 (Python Code)

Max Activating Token Index: 851