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

Dataset: The Pile

Neuron 1103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1711289 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0672. Min Act: -0.0000

Data Index: 87183 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.1376. Min Act: -0.0001

Data Index: 515724 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.1124. Min Act: -0.0000

Data Index: 677903 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0403. Min Act: -0.0000

Data Index: 784487 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1381380 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1496721 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0212. Min Act: -0.0000

Data Index: 736978 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.1058. Min Act: -0.0000

Data Index: 249925 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9248. Min Act: -0.0000

Data Index: 871982 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0443. Min Act: -0.0001

Data Index: 122325 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1327745 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0001. Min Act: -0.0001

Data Index: 238032 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1608965 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1392900 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9464. Min Act: -0.0000

Data Index: 302286 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1562755 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1216281 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9327. Min Act: -0.0000

Data Index: 83910 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9139. Min Act: -0.0001

Data Index: 1727552 (The Pile)

Max Activating Token Index: 160