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

Dataset: The Pile

Neuron 752 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: 0.6075. Min Range: -0.6075

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1959491 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5710. Min Act: -0.0000

Data Index: 185216 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4963. Min Act: 0.0000

Data Index: 1966430 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1682364 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4175. Min Act: 0.0001

Data Index: 1323178 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3921. Min Act: 0.0000

Data Index: 1591656 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1646633 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1295126 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1978651 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3831. Min Act: -0.0000

Data Index: 723573 (The Pile)

Max Activating Token Index: 266

Text #10

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3816. Min Act: -0.0000

Data Index: 736455 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1320973 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1988493 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3602. Min Act: 0.0000

Data Index: 1212034 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3677. Min Act: -0.0000

Data Index: 742951 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1659358 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1112994 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1646299 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3403. Min Act: -0.0000

Data Index: 406679 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1897189 (The Pile)

Max Activating Token Index: 874