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

Dataset: The Pile

Neuron 4815 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1170548 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3643. Min Act: -0.0000

Data Index: 57615 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1518650 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1345661 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3368. Min Act: -0.0000

Data Index: 80407 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1873822 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1600191 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3096. Min Act: -0.0000

Data Index: 236659 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3634. Min Act: -0.0000

Data Index: 436387 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3161. Min Act: -0.0000

Data Index: 888989 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3214. Min Act: -0.0000

Data Index: 986692 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3074. Min Act: -0.0000

Data Index: 686039 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3177. Min Act: -0.0000

Data Index: 889656 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1527874 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3038. Min Act: -0.0000

Data Index: 51893 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2967. Min Act: 0.0000

Data Index: 1056475 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1281911 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1981836 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2645. Min Act: -0.0000

Data Index: 636705 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2901. Min Act: -0.0000

Data Index: 770490 (The Pile)

Max Activating Token Index: 999