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

Dataset: The Pile

Neuron 1680 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.3814. Min Act: -0.0000

Data Index: 621283 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.0340. Min Act: -0.0000

Data Index: 445566 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1471814 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8644. Min Act: -0.0000

Data Index: 463551 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8926. Min Act: -0.0000

Data Index: 944697 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8440. Min Act: -0.0000

Data Index: 996146 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1022473 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1631695 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8495. Min Act: -0.0000

Data Index: 191683 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1225291 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8429. Min Act: -0.0000

Data Index: 627889 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8455. Min Act: -0.0000

Data Index: 268508 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1494645 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1469604 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1710572 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.7197. Min Act: -0.0000

Data Index: 658610 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.6094. Min Act: -0.0000

Data Index: 969456 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.5720. Min Act: -0.0000

Data Index: 712814 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1644305 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1617649 (The Pile)

Max Activating Token Index: 29