Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1602 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1507759 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1034122 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1030. Min Act: -0.0000

Data Index: 576953 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1434450 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0941. Min Act: -0.0000

Data Index: 63748 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0958. Min Act: -0.0000

Data Index: 125339 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0876. Min Act: -0.0000

Data Index: 698366 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0941. Min Act: -0.0000

Data Index: 248560 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1389771 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1524712 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0815. Min Act: -0.0000

Data Index: 873968 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0864. Min Act: -0.0000

Data Index: 907003 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0848. Min Act: -0.0000

Data Index: 82614 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1029861 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1468616 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1637703 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0846. Min Act: -0.0000

Data Index: 688325 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0845. Min Act: -0.0000

Data Index: 347216 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0838. Min Act: -0.0000

Data Index: 291344 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0836. Min Act: -0.0000

Data Index: 329445 (C4 (Web Text))

Max Activating Token Index: 797