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

Dataset: The Pile

Neuron 1782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1724. Min Act: -0.0000

Data Index: 388761 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0385. Min Act: -0.0000

Data Index: 326124 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1365583 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8508. Min Act: -0.0000

Data Index: 942376 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1786951 (The Pile)

Max Activating Token Index: 891

Text #5

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1286698 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1440196 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9310. Min Act: -0.0000

Data Index: 323663 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8509. Min Act: -0.0000

Data Index: 743650 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1018973 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1574850 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8317. Min Act: -0.0000

Data Index: 107436 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8634. Min Act: -0.0000

Data Index: 311397 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1027003 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8801. Min Act: -0.0000

Data Index: 610807 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.7700. Min Act: -0.0000

Data Index: 104938 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1241248 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8190. Min Act: -0.0000

Data Index: 355861 (The Pile)

Max Activating Token Index: 979

Text #18

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1711364 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8528. Min Act: -0.0000

Data Index: 440217 (The Pile)

Max Activating Token Index: 766