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

Dataset: The Pile

Neuron 1733 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.5068. Min Act: -0.0000

Data Index: 1302158 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1153500 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4108. Min Act: -0.0000

Data Index: 14616 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4292. Min Act: -0.0000

Data Index: 891789 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3334. Min Act: -0.0000

Data Index: 408776 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1265727 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1116491 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4447. Min Act: -0.0000

Data Index: 696151 (The Pile)

Max Activating Token Index: 861

Text #8

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3136. Min Act: -0.0000

Data Index: 956012 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3330. Min Act: -0.0000

Data Index: 1763270 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2472. Min Act: -0.0000

Data Index: 857686 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1333332 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1998907 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1160136 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1556157 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0657. Min Act: -0.0000

Data Index: 722816 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2035. Min Act: -0.0000

Data Index: 711006 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2114. Min Act: -0.0000

Data Index: 496723 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1291110 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2503. Min Act: -0.0000

Data Index: 864826 (The Pile)

Max Activating Token Index: 579