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

Dataset: The Pile

Neuron 488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.8320. Min Act: -0.0000

Data Index: 1685681 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0112. Min Act: -0.0000

Data Index: 446688 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1745461 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1433725 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1148592 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9500. Min Act: -0.0000

Data Index: 463163 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9675. Min Act: -0.0000

Data Index: 162257 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1808579 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1077725 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1677787 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1726384 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8749. Min Act: -0.0000

Data Index: 686784 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9616. Min Act: -0.0000

Data Index: 238202 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1649683 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8860. Min Act: -0.0000

Data Index: 426681 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1534904 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1646241 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.8641. Min Act: -0.0000

Data Index: 20435 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1490204 (The Pile)

Max Activating Token Index: 401

Text #19

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1606951 (The Pile)

Max Activating Token Index: 828