Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1947 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1217959 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0914. Min Act: -0.0002

Data Index: 504104 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1149989 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1194045 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1086012 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0855. Min Act: -0.0002

Data Index: 245120 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0879. Min Act: -0.0002

Data Index: 329279 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0781. Min Act: -0.0002

Data Index: 121660 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0767. Min Act: -0.0002

Data Index: 553180 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0719. Min Act: -0.0002

Data Index: 471345 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0762. Min Act: -0.0002

Data Index: 500471 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0688. Min Act: -0.0002

Data Index: 75955 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0684. Min Act: -0.0002

Data Index: 911239 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0687. Min Act: -0.0002

Data Index: 864807 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1358414 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0683. Min Act: -0.0002

Data Index: 858596 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0659. Min Act: -0.0002

Data Index: 454506 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0665. Min Act: -0.0002

Data Index: 59181 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0672. Min Act: -0.0002

Data Index: 42306 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0626. Min Act: -0.0002

Data Index: 737689 (C4 (Web Text))

Max Activating Token Index: 301