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

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

Neuron 1896 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0000

Data Index: 820146 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0814. Min Act: -0.0000

Data Index: 547036 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0663. Min Act: -0.0000

Data Index: 782926 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1027113 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1086991 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1588103 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1391341 (Python Code)

Max Activating Token Index: 977

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1580771 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1411217 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1563388 (Python Code)

Max Activating Token Index: 629

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0550. Min Act: -0.0000

Data Index: 22777 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1122378 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0532. Min Act: -0.0000

Data Index: 166490 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0537. Min Act: -0.0000

Data Index: 390279 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0529. Min Act: -0.0000

Data Index: 350205 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1410493 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0542. Min Act: -0.0000

Data Index: 531597 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0507. Min Act: -0.0000

Data Index: 609715 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1478651 (Python Code)

Max Activating Token Index: 894

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0515. Min Act: -0.0000

Data Index: 363279 (C4 (Web Text))

Max Activating Token Index: 435