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

Dataset: The Pile

Neuron 101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1278602 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1832789 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8527. Min Act: -0.0000

Data Index: 201725 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1078890 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8968. Min Act: -0.0000

Data Index: 78822 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1024611 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1606510 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8351. Min Act: -0.0000

Data Index: 495792 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1595597 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1648870 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1096656 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8043. Min Act: -0.0000

Data Index: 637093 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1727045 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1660699 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1769947 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1728338 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1012860 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9106. Min Act: -0.0000

Data Index: 310715 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7882. Min Act: -0.0000

Data Index: 694477 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1784447 (The Pile)

Max Activating Token Index: 896