Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 40 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0002

Data Index: 1126084 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1819. Min Act: -0.0002

Data Index: 465147 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1672. Min Act: -0.0002

Data Index: 497328 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1675. Min Act: -0.0002

Data Index: 638602 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1633. Min Act: -0.0002

Data Index: 563476 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1621. Min Act: -0.0002

Data Index: 623944 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1788. Min Act: -0.0002

Data Index: 921077 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1587. Min Act: -0.0002

Data Index: 396267 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1074207 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1560. Min Act: -0.0002

Data Index: 983571 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1540. Min Act: -0.0002

Data Index: 183082 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1453. Min Act: -0.0002

Data Index: 345433 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1561. Min Act: -0.0002

Data Index: 1231089 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1607. Min Act: -0.0002

Data Index: 986199 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1359. Min Act: -0.0002

Data Index: 1337812 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1422. Min Act: -0.0002

Data Index: 878871 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1577. Min Act: -0.0002

Data Index: 912163 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1472. Min Act: -0.0002

Data Index: 873784 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1447. Min Act: -0.0002

Data Index: 1151742 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1386. Min Act: -0.0002

Data Index: 520423 (C4 (Web Text))

Max Activating Token Index: 977