Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5032 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.8066. Min Act: -0.0000

Data Index: 314891 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.4228. Min Act: -0.0000

Data Index: 94009 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.6970. Min Act: -0.0000

Data Index: 1034356 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.5206. Min Act: -0.0000

Data Index: 550406 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.1877. Min Act: -0.0000

Data Index: 1253236 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.3317. Min Act: -0.0000

Data Index: 44630 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.1593. Min Act: -0.0000

Data Index: 654063 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.1110. Min Act: -0.0000

Data Index: 1048159 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.0999. Min Act: -0.0000

Data Index: 522554 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.0667. Min Act: -0.0000

Data Index: 474945 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.0550. Min Act: -0.0000

Data Index: 280964 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.1840. Min Act: -0.0000

Data Index: 1157351 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.0026. Min Act: -0.0000

Data Index: 732600 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1244294 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.0218. Min Act: -0.0000

Data Index: 219417 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 3.8066. Min Range: -3.8066

Max Act: 3.0063. Min Act: -0.0000

Data Index: 445114 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 3.8066. Min Range: -3.8066

Max Act: 2.8602. Min Act: -0.0000

Data Index: 513562 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 3.8066. Min Range: -3.8066

Max Act: 2.9774. Min Act: -0.0000

Data Index: 413493 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.8066. Min Range: -3.8066

Max Act: 2.9629. Min Act: -0.0000

Data Index: 30497 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 3.8066. Min Range: -3.8066

Max Act: 2.9543. Min Act: -0.0000

Data Index: 400405 (C4 (Web Text))

Max Activating Token Index: 602