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

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

Neuron 1847 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0802. Min Act: -0.0001

Data Index: 145836 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0747. Min Act: -0.0001

Data Index: 854581 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1222791 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0708. Min Act: -0.0002

Data Index: 957312 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0689. Min Act: -0.0002

Data Index: 328798 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0663. Min Act: -0.0001

Data Index: 682964 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0663. Min Act: -0.0002

Data Index: 981072 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1011147 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0641. Min Act: -0.0001

Data Index: 202528 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1290074 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0656. Min Act: -0.0001

Data Index: 831850 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0604. Min Act: -0.0001

Data Index: 228480 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0628. Min Act: -0.0002

Data Index: 588795 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0651. Min Act: -0.0002

Data Index: 80668 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0677. Min Act: -0.0002

Data Index: 676580 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1346595 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1282881 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0660. Min Act: -0.0002

Data Index: 795139 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0631. Min Act: -0.0001

Data Index: 729109 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1226386 (C4 (Web Text))

Max Activating Token Index: 289