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

Dataset: The Pile

Neuron 1225 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: 1.1560. Min Range: -1.1560

Max Act: 1.1560. Min Act: -0.0000

Data Index: 664175 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0706. Min Act: -0.0000

Data Index: 226906 (The Pile)

Max Activating Token Index: 809

Text #2

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1828596 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1472429 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0258. Min Act: -0.0000

Data Index: 714265 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9828. Min Act: -0.0000

Data Index: 912839 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9670. Min Act: -0.0000

Data Index: 331227 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9574. Min Act: -0.0000

Data Index: 917788 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9947. Min Act: -0.0000

Data Index: 299121 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9531. Min Act: -0.0000

Data Index: 885791 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1181997 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8875. Min Act: -0.0000

Data Index: 740126 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8850. Min Act: -0.0000

Data Index: 851530 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8386. Min Act: -0.0000

Data Index: 141370 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1503296 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1149136 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1413440 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1891982 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1337461 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8347. Min Act: 0.0000

Data Index: 942118 (The Pile)

Max Activating Token Index: 202