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

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

Neuron 616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0005

Data Index: 945133 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0645. Min Act: -0.0005

Data Index: 1071704 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0647. Min Act: -0.0005

Data Index: 1304423 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0622. Min Act: -0.0005

Data Index: 338994 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0643. Min Act: -0.0005

Data Index: 324702 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0609. Min Act: -0.0005

Data Index: 194448 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0620. Min Act: -0.0005

Data Index: 252553 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0602. Min Act: -0.0005

Data Index: 1040993 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0579. Min Act: -0.0005

Data Index: 1049318 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0575. Min Act: -0.0005

Data Index: 1224918 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0558. Min Act: -0.0005

Data Index: 1248615 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0596. Min Act: -0.0005

Data Index: 849104 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0572. Min Act: -0.0005

Data Index: 569165 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0557. Min Act: -0.0005

Data Index: 913953 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0544. Min Act: -0.0005

Data Index: 44499 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0570. Min Act: -0.0005

Data Index: 790561 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0567. Min Act: -0.0005

Data Index: 101291 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0550. Min Act: -0.0005

Data Index: 790577 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0537. Min Act: -0.0005

Data Index: 1131900 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0583. Min Act: -0.0005

Data Index: 106366 (C4 (Web Text))

Max Activating Token Index: 449