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

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

Neuron 2082 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: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1201105 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0837. Min Act: -0.0002

Data Index: 706588 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1162065 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0735. Min Act: -0.0002

Data Index: 801823 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0697. Min Act: -0.0002

Data Index: 391785 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1307244 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0672. Min Act: -0.0002

Data Index: 436355 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0620. Min Act: -0.0002

Data Index: 363106 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0639. Min Act: -0.0002

Data Index: 528579 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0629. Min Act: -0.0002

Data Index: 657322 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0602. Min Act: -0.0002

Data Index: 813679 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0571. Min Act: -0.0002

Data Index: 78290 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0586. Min Act: -0.0002

Data Index: 924034 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1063682 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0544. Min Act: -0.0002

Data Index: 844698 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0543. Min Act: -0.0002

Data Index: 782689 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0553. Min Act: -0.0002

Data Index: 703508 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0543. Min Act: -0.0002

Data Index: 113474 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0529. Min Act: -0.0002

Data Index: 238153 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0560. Min Act: -0.0002

Data Index: 626940 (C4 (Web Text))

Max Activating Token Index: 828