Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 573 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0003

Data Index: 1414781 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1618735 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0628. Min Act: -0.0003

Data Index: 771928 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1429824 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1330746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1352832 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0541. Min Act: -0.0003

Data Index: 76990 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1602623 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1586734 (Python Code)

Max Activating Token Index: 765

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0547. Min Act: -0.0002

Data Index: 4332 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0558. Min Act: -0.0003

Data Index: 680015 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1504674 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1635193 (Python Code)

Max Activating Token Index: 402

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1515510 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1620907 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1406683 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1437944 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1648460 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0512. Min Act: -0.0003

Data Index: 551658 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0525. Min Act: -0.0004

Data Index: 1051544 (C4 (Web Text))

Max Activating Token Index: 1002