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

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

Neuron 200 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0003

Data Index: 701974 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1088646 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0632. Min Act: -0.0002

Data Index: 446695 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0631. Min Act: -0.0003

Data Index: 285460 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1014402 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0608. Min Act: -0.0003

Data Index: 181164 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1259374 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0585. Min Act: -0.0003

Data Index: 794156 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0558. Min Act: -0.0003

Data Index: 942934 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0568. Min Act: -0.0003

Data Index: 64405 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0563. Min Act: -0.0003

Data Index: 436584 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0544. Min Act: -0.0003

Data Index: 232568 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0563. Min Act: -0.0003

Data Index: 890977 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0550. Min Act: -0.0002

Data Index: 996190 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0538. Min Act: -0.0003

Data Index: 351722 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1038614 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0547. Min Act: -0.0003

Data Index: 21891 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0535. Min Act: -0.0003

Data Index: 423406 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0527. Min Act: -0.0003

Data Index: 839554 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0547. Min Act: -0.0003

Data Index: 806521 (C4 (Web Text))

Max Activating Token Index: 524