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

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

Neuron 800 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1462686 (Python Code)

Max Activating Token Index: 555

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1554639 (Python Code)

Max Activating Token Index: 909

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1460808 (Python Code)

Max Activating Token Index: 361

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1421890 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1604852 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1064. Min Act: -0.0001

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1017. Min Act: -0.0001

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1624351 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1077. Min Act: -0.0001

Data Index: 47829 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1029. Min Act: -0.0001

Data Index: 5921 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1538449 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1070249 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1645897 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1212109 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0994. Min Act: -0.0001

Data Index: 837914 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1454772 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1007452 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1584573 (Python Code)

Max Activating Token Index: 618

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0944. Min Act: -0.0001

Data Index: 317232 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1502642 (Python Code)

Max Activating Token Index: 395