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

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

Neuron 1300 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: 0.7620. Min Range: -0.7620

Max Act: 0.7618. Min Act: -0.0002

Data Index: 736184 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.7620. Min Act: -0.0002

Data Index: 869225 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.7126. Min Act: -0.0002

Data Index: 121360 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.7054. Min Act: -0.0002

Data Index: 1325045 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6823. Min Act: -0.0002

Data Index: 961398 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6841. Min Act: -0.0002

Data Index: 535509 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6883. Min Act: -0.0002

Data Index: 517364 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6718. Min Act: -0.0002

Data Index: 862795 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6726. Min Act: -0.0002

Data Index: 101357 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6769. Min Act: -0.0002

Data Index: 1449871 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6769. Min Act: -0.0002

Data Index: 482431 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6776. Min Act: -0.0002

Data Index: 645649 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6758. Min Act: -0.0002

Data Index: 1022180 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6611. Min Act: -0.0002

Data Index: 824601 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6554. Min Act: -0.0002

Data Index: 631179 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6484. Min Act: -0.0002

Data Index: 1231367 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6488. Min Act: -0.0002

Data Index: 1321801 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6438. Min Act: -0.0002

Data Index: 879747 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6449. Min Act: -0.0002

Data Index: 1349945 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6491. Min Act: -0.0002

Data Index: 1101009 (C4 (Web Text))

Max Activating Token Index: 834