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

Dataset: The Pile

Neuron 1743 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1463163 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2954. Min Act: 0.0000

Data Index: 382295 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3419. Min Act: -0.0000

Data Index: 969694 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2886. Min Act: -0.0000

Data Index: 714177 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1871301 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2787. Min Act: -0.0000

Data Index: 101033 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2847. Min Act: -0.0000

Data Index: 554621 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2728. Min Act: -0.0000

Data Index: 103426 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1086348 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1525194 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1754555 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2688. Min Act: -0.0000

Data Index: 541066 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2678. Min Act: -0.0000

Data Index: 755512 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2509. Min Act: -0.0000

Data Index: 300837 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2599. Min Act: -0.0000

Data Index: 529144 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1120116 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1533494 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2497. Min Act: -0.0000

Data Index: 937962 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1861393 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1816324 (The Pile)

Max Activating Token Index: 333