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

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

Neuron 5000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0002

Data Index: 982608 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0691. Min Act: -0.0002

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0710. Min Act: -0.0002

Data Index: 926214 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0735. Min Act: -0.0002

Data Index: 556109 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0685. Min Act: -0.0002

Data Index: 346557 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0711. Min Act: -0.0002

Data Index: 873318 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1034780 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1212536 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0608. Min Act: -0.0002

Data Index: 19231 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0624. Min Act: -0.0002

Data Index: 659251 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0642. Min Act: -0.0002

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0689. Min Act: -0.0002

Data Index: 342113 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0638. Min Act: -0.0002

Data Index: 801048 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0641. Min Act: -0.0002

Data Index: 658564 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0558. Min Act: -0.0002

Data Index: 503935 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0615. Min Act: -0.0002

Data Index: 420493 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1251558 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0609. Min Act: -0.0002

Data Index: 761588 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1298783 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0679. Min Act: -0.0002

Data Index: 99008 (C4 (Web Text))

Max Activating Token Index: 1020