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

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

Neuron 3766 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1447271 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1622184 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1539034 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1429911 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1626149 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1577832 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1380862 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1549193 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1421162 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1642129 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1392510 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1620082 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1542534 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1554859 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1595049 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1556072 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1584306 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1379926 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1603190 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1441873 (Python Code)

Max Activating Token Index: 6