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

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

Neuron 1345 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0003

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1368324 (Python Code)

Max Activating Token Index: 153

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1222905 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0624. Min Act: -0.0003

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0608. Min Act: -0.0003

Data Index: 111455 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0653. Min Act: -0.0003

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0608. Min Act: -0.0002

Data Index: 601719 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0609. Min Act: -0.0002

Data Index: 822661 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0581. Min Act: -0.0003

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0599. Min Act: -0.0003

Data Index: 877862 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0586. Min Act: -0.0002

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0572. Min Act: -0.0003

Data Index: 43978 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1069643 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1170184 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1172912 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0581. Min Act: -0.0003

Data Index: 47411 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1475269 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1092376 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0552. Min Act: -0.0003

Data Index: 789325 (C4 (Web Text))

Max Activating Token Index: 701