Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3914 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0002

Data Index: 412519 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0794. Min Act: -0.0002

Data Index: 364008 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1556583 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0604. Min Act: -0.0001

Data Index: 833415 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0636. Min Act: -0.0002

Data Index: 232079 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1535064 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0616. Min Act: -0.0001

Data Index: 303885 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1220312 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1234464 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0608. Min Act: -0.0002

Data Index: 980571 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1264288 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0624. Min Act: -0.0002

Data Index: 149625 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0598. Min Act: -0.0002

Data Index: 33017 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1031589 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1544017 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1088860 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0615. Min Act: -0.0001

Data Index: 928389 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0654. Min Act: -0.0002

Data Index: 76334 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0597. Min Act: -0.0001

Data Index: 218185 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1493139 (Python Code)

Max Activating Token Index: 814