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

Dataset: The Pile

Neuron 4468 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: 4.7656. Min Range: -4.7656

Max Act: 4.7656. Min Act: -0.0000

Data Index: 935670 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.0134. Min Act: -0.0000

Data Index: 1654127 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.7828. Min Act: -0.0000

Data Index: 1187235 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.7742. Min Act: -0.0000

Data Index: 488616 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.6084. Min Act: -0.0000

Data Index: 60312 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.7768. Min Act: -0.0000

Data Index: 503397 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.6905. Min Act: -0.0000

Data Index: 126086 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.4757. Min Act: -0.0000

Data Index: 313305 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.3022. Min Act: -0.0000

Data Index: 1054767 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.2533. Min Act: -0.0000

Data Index: 971649 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.3918. Min Act: -0.0000

Data Index: 534831 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.6605. Min Act: -0.0000

Data Index: 847147 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.6663. Min Act: -0.0000

Data Index: 1255528 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.2768. Min Act: -0.0000

Data Index: 303257 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.5045. Min Act: -0.0000

Data Index: 1182372 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.6580. Min Act: 0.0000

Data Index: 1562526 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.4862. Min Act: -0.0000

Data Index: 1590144 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.4516. Min Act: -0.0000

Data Index: 1458703 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.2785. Min Act: -0.0000

Data Index: 1623837 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.1149. Min Act: -0.0000

Data Index: 2295 (The Pile)

Max Activating Token Index: 916