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

Dataset: The Pile

Neuron 516 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: 0.4675. Min Range: -0.4675

Max Act: 0.4675. Min Act: -0.0000

Data Index: 264578 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1351812 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3857. Min Act: -0.0000

Data Index: 596052 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1959108 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3788. Min Act: -0.0000

Data Index: 849523 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1292376 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3696. Min Act: -0.0000

Data Index: 292208 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1976356 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1440084 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3600. Min Act: -0.0000

Data Index: 489165 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3591. Min Act: -0.0000

Data Index: 806585 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1436985 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1554586 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3524. Min Act: 0.0000

Data Index: 1865923 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1958476 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3206. Min Act: -0.0000

Data Index: 944277 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3504. Min Act: -0.0000

Data Index: 874391 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1543856 (The Pile)

Max Activating Token Index: 780

Text #18

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1718712 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1654255 (The Pile)

Max Activating Token Index: 623