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

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

Neuron 4144 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1528226 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1430714 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0585. Min Act: -0.0002

Data Index: 223912 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0577. Min Act: -0.0002

Data Index: 921711 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0582. Min Act: -0.0002

Data Index: 167130 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0570. Min Act: -0.0002

Data Index: 864523 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0570. Min Act: -0.0002

Data Index: 936461 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0552. Min Act: -0.0002

Data Index: 19991 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1495571 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0552. Min Act: -0.0002

Data Index: 290558 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0552. Min Act: -0.0002

Data Index: 234005 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1204649 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0552. Min Act: -0.0002

Data Index: 995294 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1622314 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1167251 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1046743 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0534. Min Act: -0.0002

Data Index: 884200 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0540. Min Act: -0.0002

Data Index: 657657 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1648088 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1118609 (C4 (Web Text))

Max Activating Token Index: 558