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

Dataset: The Pile

Neuron 3829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5671. Min Act: -0.0000

Data Index: 662596 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5490. Min Act: -0.0000

Data Index: 935837 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5061. Min Act: -0.0000

Data Index: 135499 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1029084 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1601733 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1136903 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1519449 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1840892 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1775197 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1006614 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3978. Min Act: -0.0000

Data Index: 986464 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1124575 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3931. Min Act: -0.0000

Data Index: 570527 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3981. Min Act: -0.0000

Data Index: 703080 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3900. Min Act: -0.0000

Data Index: 690071 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3865. Min Act: -0.0000

Data Index: 678128 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3988. Min Act: -0.0000

Data Index: 742368 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1212516 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3951. Min Act: -0.0000

Data Index: 186150 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.3761. Min Act: -0.0000

Data Index: 757119 (The Pile)

Max Activating Token Index: 186