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

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

Neuron 3849 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1118329 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0761. Min Act: -0.0000

Data Index: 218128 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1210673 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0538. Min Act: -0.0000

Data Index: 107987 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0588. Min Act: -0.0000

Data Index: 250953 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0586. Min Act: -0.0000

Data Index: 533816 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0560. Min Act: -0.0000

Data Index: 593591 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0553. Min Act: -0.0000

Data Index: 275387 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0550. Min Act: -0.0000

Data Index: 642011 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0533. Min Act: -0.0000

Data Index: 926546 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1468554 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0540. Min Act: -0.0000

Data Index: 995041 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1505601 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0519. Min Act: -0.0000

Data Index: 355412 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0470. Min Act: -0.0000

Data Index: 947690 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0566. Min Act: -0.0000

Data Index: 80997 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1604322 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0491. Min Act: -0.0000

Data Index: 444467 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1188376 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0508. Min Act: -0.0000

Data Index: 206379 (C4 (Web Text))

Max Activating Token Index: 714