Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 999 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1091. Min Act: -0.0003

Data Index: 638938 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0002

Data Index: 811762 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1060. Min Act: -0.0003

Data Index: 657178 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0792. Min Act: -0.0003

Data Index: 358995 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0807. Min Act: -0.0003

Data Index: 840374 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0803. Min Act: -0.0003

Data Index: 548390 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0805. Min Act: -0.0003

Data Index: 447192 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1049489 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0771. Min Act: -0.0003

Data Index: 363222 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0779. Min Act: -0.0003

Data Index: 524856 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0739. Min Act: -0.0003

Data Index: 24042 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0743. Min Act: -0.0002

Data Index: 604558 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1143511 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0707. Min Act: -0.0003

Data Index: 127107 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0700. Min Act: -0.0003

Data Index: 510018 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0695. Min Act: -0.0004

Data Index: 373412 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0747. Min Act: -0.0003

Data Index: 11473 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1337556 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1226100 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0731. Min Act: -0.0002

Data Index: 541242 (C4 (Web Text))

Max Activating Token Index: 551