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

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

Neuron 4985 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1470459 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0576. Min Act: -0.0000

Data Index: 98476 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1119781 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0574. Min Act: -0.0000

Data Index: 212589 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1618438 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0509. Min Act: -0.0000

Data Index: 796196 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1554296 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1446949 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1370070 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1475012 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1429789 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1454422 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0513. Min Act: -0.0000

Data Index: 950528 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0525. Min Act: -0.0000

Data Index: 829744 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1455971 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0500. Min Act: -0.0000

Data Index: 636272 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0524. Min Act: -0.0000

Data Index: 455006 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1620196 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1394587 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1538013 (Python Code)

Max Activating Token Index: 878