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

Dataset: The Pile

Neuron 2487 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: 1.7453. Min Range: -1.7453

Max Act: 1.4116. Min Act: -0.0000

Data Index: 988377 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.7453. Min Act: -0.0000

Data Index: 472334 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.6498. Min Act: -0.0000

Data Index: 996826 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.6565. Min Act: -0.0000

Data Index: 1810312 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5687. Min Act: -0.0000

Data Index: 867205 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5557. Min Act: -0.0000

Data Index: 97705 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4637. Min Act: -0.0000

Data Index: 389863 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1578406 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3033. Min Act: -0.0000

Data Index: 580397 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4910. Min Act: -0.0000

Data Index: 682193 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1518143 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4744. Min Act: -0.0000

Data Index: 714036 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5488. Min Act: -0.0000

Data Index: 844017 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4850. Min Act: -0.0000

Data Index: 790984 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1837625 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4516. Min Act: -0.0000

Data Index: 852387 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4250. Min Act: -0.0000

Data Index: 269864 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4314. Min Act: -0.0000

Data Index: 1077912 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4987. Min Act: -0.0000

Data Index: 1418780 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4105. Min Act: -0.0000

Data Index: 581589 (The Pile)

Max Activating Token Index: 974