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

Dataset: The Pile

Neuron 1218 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: 7.5487. Min Range: -7.5487

Max Act: 7.5487. Min Act: -0.0000

Data Index: 393569 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.8952. Min Act: -0.0000

Data Index: 1695737 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.4604. Min Act: -0.0000

Data Index: 192699 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.5532. Min Act: -0.0000

Data Index: 1860062 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.4122. Min Act: -0.0000

Data Index: 1528009 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.4194. Min Act: -0.0000

Data Index: 1097950 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.1776. Min Act: -0.0000

Data Index: 532398 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.0266. Min Act: -0.0000

Data Index: 1451637 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 7.5487. Min Range: -7.5487

Max Act: 5.9013. Min Act: -0.0000

Data Index: 591747 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.0000. Min Act: -0.0000

Data Index: 41910 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.0320. Min Act: -0.0000

Data Index: 1146084 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 7.5487. Min Range: -7.5487

Max Act: 4.5816. Min Act: -0.0000

Data Index: 1881072 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 7.5487. Min Range: -7.5487

Max Act: 5.6747. Min Act: -0.0000

Data Index: 272361 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.0187. Min Act: -0.0000

Data Index: 1487772 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.1732. Min Act: -0.0000

Data Index: 1020028 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 7.5487. Min Range: -7.5487

Max Act: 6.1609. Min Act: -0.0000

Data Index: 602574 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 7.5487. Min Range: -7.5487

Max Act: 5.3658. Min Act: -0.0000

Data Index: 854435 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 7.5487. Min Range: -7.5487

Max Act: 5.4430. Min Act: -0.0000

Data Index: 474228 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 7.5487. Min Range: -7.5487

Max Act: 5.4355. Min Act: -0.0000

Data Index: 1840716 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 7.5487. Min Range: -7.5487

Max Act: 5.7993. Min Act: -0.0000

Data Index: 1861003 (The Pile)

Max Activating Token Index: 76