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

Dataset: The Pile

Neuron 2794 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: 1.1324. Min Range: -1.1324

Max Act: 1.1324. Min Act: -0.0000

Data Index: 666925 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9640. Min Act: -0.0000

Data Index: 128910 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1994162 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1204800 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9887. Min Act: -0.0000

Data Index: 979276 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9148. Min Act: -0.0000

Data Index: 960078 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9017. Min Act: -0.0000

Data Index: 778073 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1423803 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1206336 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1027727 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1760572 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1279764 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9609. Min Act: -0.0000

Data Index: 580588 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8694. Min Act: -0.0000

Data Index: 461303 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8547. Min Act: -0.0000

Data Index: 610682 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7366. Min Act: -0.0000

Data Index: 564555 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0202. Min Act: -0.0000

Data Index: 134577 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8199. Min Act: -0.0000

Data Index: 266576 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8357. Min Act: -0.0000

Data Index: 563461 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8092. Min Act: -0.0000

Data Index: 338222 (The Pile)

Max Activating Token Index: 508