Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2087. Min Act: 0.0000

Data Index: 1847923 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1313. Min Act: -0.0000

Data Index: 336946 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1269. Min Act: -0.0001

Data Index: 810780 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1258758 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1320. Min Act: -0.0000

Data Index: 17589 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1368776 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1703254 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1419092 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1025. Min Act: -0.0000

Data Index: 737172 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1679380 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1021. Min Act: -0.0000

Data Index: 314462 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1665847 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0909. Min Act: -0.0000

Data Index: 67519 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0983. Min Act: 0.0000

Data Index: 871871 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1279822 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1132793 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0875. Min Act: -0.0000

Data Index: 59197 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1111929 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1651658 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1026780 (The Pile)

Max Activating Token Index: 728