Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1545 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.6676. Min Act: -0.0000

Data Index: 586430 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.6284. Min Act: -0.0000

Data Index: 527724 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5671. Min Act: -0.0000

Data Index: 458464 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1677427 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1810934 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4735. Min Act: -0.0000

Data Index: 666653 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4860. Min Act: -0.0000

Data Index: 152649 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4678. Min Act: -0.0000

Data Index: 755279 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1685037 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1124160 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1764633 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1273479 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1967222 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4671. Min Act: -0.0000

Data Index: 466836 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1679073 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4412. Min Act: -0.0000

Data Index: 329487 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4509. Min Act: -0.0000

Data Index: 608798 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1121065 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4741. Min Act: -0.0000

Data Index: 700430 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.6676. Min Range: -0.6676

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1784196 (The Pile)

Max Activating Token Index: 502