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

Dataset: The Pile

Neuron 531 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: 0.3539. Min Range: -0.3539

Max Act: 0.3539. Min Act: -0.0000

Data Index: 135934 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1845059 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1752542 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1065175 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1618072 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3175. Min Act: -0.0000

Data Index: 242878 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1650691 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1776337 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2911. Min Act: -0.0000

Data Index: 517543 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3089. Min Act: -0.0000

Data Index: 247021 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2985. Min Act: -0.0000

Data Index: 806840 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1899695 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3108. Min Act: -0.0000

Data Index: 540504 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1564212 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1165962 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2832. Min Act: -0.0000

Data Index: 536079 (The Pile)

Max Activating Token Index: 985

Text #16

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1309034 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1821861 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2888. Min Act: -0.0000

Data Index: 294523 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1146361 (The Pile)

Max Activating Token Index: 627