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

Dataset: The Pile

Neuron 3479 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: 1.1013. Min Range: -1.1013

Max Act: 1.1013. Min Act: -0.0000

Data Index: 617071 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 1.1013. Min Range: -1.1013

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1436389 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.1013. Min Range: -1.1013

Max Act: 1.0888. Min Act: -0.0000

Data Index: 872093 (The Pile)

Max Activating Token Index: 878

Text #3

Max Range: 1.1013. Min Range: -1.1013

Max Act: 1.0964. Min Act: -0.0000

Data Index: 891657 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 1.1013. Min Range: -1.1013

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1009295 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1348568 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1494482 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1327947 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1287518 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1277373 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1677705 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9287. Min Act: -0.0000

Data Index: 719680 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1006063 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1319012 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8781. Min Act: -0.0000

Data Index: 424606 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1608688 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8953. Min Act: -0.0000

Data Index: 80200 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8114. Min Act: -0.0000

Data Index: 87643 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8824. Min Act: -0.0000

Data Index: 71773 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7984. Min Act: -0.0000

Data Index: 743384 (The Pile)

Max Activating Token Index: 222