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

Dataset: The Pile

Neuron 4539 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0121. Min Range: -1.0121

Max Act: 1.0121. Min Act: -0.0000

Data Index: 433898 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 1.0121. Min Range: -1.0121

Max Act: 1.0048. Min Act: -0.0000

Data Index: 861376 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1880129 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.9518. Min Act: -0.0000

Data Index: 63409 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1785457 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1743583 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1114443 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8468. Min Act: -0.0000

Data Index: 390260 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8373. Min Act: -0.0000

Data Index: 585381 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1353128 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8590. Min Act: -0.0000

Data Index: 397932 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1845386 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8203. Min Act: -0.0000

Data Index: 851147 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1600749 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1882997 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1264751 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8204. Min Act: -0.0000

Data Index: 721096 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1071558 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1712805 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1702977 (The Pile)

Max Activating Token Index: 422