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

Dataset: The Pile

Neuron 1773 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: 1.3677. Min Range: -1.3677

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1828683 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.2974. Min Act: -0.0000

Data Index: 401657 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1294. Min Act: -0.0000

Data Index: 791475 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1183012 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1636739 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1362351 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1075514 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1556625 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1407442 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1192341 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1015336 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1824801 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8827. Min Act: -0.0000

Data Index: 117030 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1253908 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.9360. Min Act: -0.0000

Data Index: 416479 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8656. Min Act: -0.0000

Data Index: 104847 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1820767 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8768. Min Act: -0.0000

Data Index: 159654 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8245. Min Act: -0.0000

Data Index: 972724 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 1.3677. Min Range: -1.3677

Max Act: 0.8034. Min Act: -0.0000

Data Index: 466955 (The Pile)

Max Activating Token Index: 964