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

Dataset: The Pile

Neuron 2943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4731. Min Act: -0.0000

Data Index: 590776 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4116. Min Act: -0.0000

Data Index: 614434 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1458269 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4117. Min Act: -0.0000

Data Index: 899477 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3370. Min Act: -0.0000

Data Index: 363981 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1182009 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1486334 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1983889 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3252. Min Act: -0.0000

Data Index: 169439 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1131899 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1227744 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3105. Min Act: -0.0000

Data Index: 337546 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3319. Min Act: -0.0000

Data Index: 622246 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3090. Min Act: -0.0000

Data Index: 471693 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2864. Min Act: -0.0000

Data Index: 263224 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1128858 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2832. Min Act: -0.0000

Data Index: 519052 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1754824 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1128233 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2807. Min Act: -0.0000

Data Index: 38242 (The Pile)

Max Activating Token Index: 497