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

Dataset: The Pile

Neuron 661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1398236 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1229830 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1120. Min Act: -0.0000

Data Index: 2369 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1044. Min Act: -0.0000

Data Index: 291810 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1873538 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1410167 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1609903 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1031. Min Act: -0.0000

Data Index: 159631 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0987. Min Act: -0.0000

Data Index: 192169 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1851891 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0994. Min Act: -0.0000

Data Index: 242983 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0899. Min Act: -0.0000

Data Index: 727178 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1613750 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1633153 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0988. Min Act: -0.0000

Data Index: 274374 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0913. Min Act: -0.0000

Data Index: 128520 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1174741 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0971. Min Act: -0.0000

Data Index: 211605 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0932. Min Act: -0.0000

Data Index: 390950 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1653478 (The Pile)

Max Activating Token Index: 214