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

Dataset: The Pile

Neuron 536 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: 1.7984. Min Range: -1.7984

Max Act: 1.7984. Min Act: -0.0000

Data Index: 1818134 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1066055 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1426378 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.5744. Min Act: -0.0000

Data Index: 532630 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1124647 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.2267. Min Act: -0.0000

Data Index: 568829 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.1812. Min Act: -0.0000

Data Index: 317087 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1915592 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.1518. Min Act: -0.0000

Data Index: 1215577 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1902258 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.1028. Min Act: -0.0000

Data Index: 212349 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.1028. Min Act: -0.0000

Data Index: 155473 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.1060. Min Act: -0.0000

Data Index: 324571 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1361867 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1557194 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.0179. Min Act: -0.0000

Data Index: 246095 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.0661. Min Act: -0.0000

Data Index: 272061 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.0627. Min Act: -0.0000

Data Index: 398860 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1578546 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 1.7984. Min Range: -1.7984

Max Act: 0.9615. Min Act: -0.0000

Data Index: 114390 (The Pile)

Max Activating Token Index: 734