Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2810 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1608559 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1463520 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1384980 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1532676 (Python Code)

Max Activating Token Index: 457

Text #4

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1373214 (Python Code)

Max Activating Token Index: 251

Text #5

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0207. Min Act: -0.0001

Data Index: 1445674 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1582560 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1466715 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1435557 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1462842 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9744. Min Act: -0.0001

Data Index: 1507909 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1367820 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 1.2089. Min Range: -1.2089

Max Act: 1.0039. Min Act: -0.0001

Data Index: 1593451 (Python Code)

Max Activating Token Index: 259

Text #13

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1563433 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1506123 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1386036 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1419934 (Python Code)

Max Activating Token Index: 809

Text #17

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9660. Min Act: -0.0001

Data Index: 1466819 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 1.2089. Min Range: -1.2089

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1485945 (Python Code)

Max Activating Token Index: 76