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

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

Neuron 1963 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1065696 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0954. Min Act: -0.0001

Data Index: 396436 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1460000 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1653986 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1528402 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1409511 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1445260 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1542589 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1532856 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1618194 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1583156 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1569018 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1430492 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1368158 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1519365 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1637050 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1581214 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1538239 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1446908 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1455552 (Python Code)

Max Activating Token Index: 996