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

Dataset: The Pile

Neuron 2306 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1258818 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1003690 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1951102 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1044334 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1017927 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5659. Min Act: -0.0000

Data Index: 667539 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5868. Min Act: -0.0000

Data Index: 909674 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1644409 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5667. Min Act: -0.0000

Data Index: 331879 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5572. Min Act: -0.0000

Data Index: 470958 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1900516 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5223. Min Act: -0.0000

Data Index: 651356 (The Pile)

Max Activating Token Index: 36

Text #12

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1169722 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4709. Min Act: -0.0000

Data Index: 89157 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1193102 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1446087 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5067. Min Act: -0.0000

Data Index: 337045 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4897. Min Act: 0.0001

Data Index: 347103 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1095424 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5015. Min Act: 0.0000

Data Index: 1860309 (The Pile)

Max Activating Token Index: 36