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

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

Neuron 382 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.8170. Min Act: -0.0000

Data Index: 710904 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7934. Min Act: -0.0000

Data Index: 882922 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.8011. Min Act: -0.0000

Data Index: 248936 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7860. Min Act: -0.0000

Data Index: 435479 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7602. Min Act: -0.0000

Data Index: 149431 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7755. Min Act: -0.0000

Data Index: 234691 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7511. Min Act: -0.0000

Data Index: 679079 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7854. Min Act: -0.0000

Data Index: 41165 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7373. Min Act: -0.0000

Data Index: 733883 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7537. Min Act: -0.0000

Data Index: 784196 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1105156 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7047. Min Act: -0.0000

Data Index: 619180 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1186718 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.6921. Min Act: -0.0000

Data Index: 218628 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1590587 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.6811. Min Act: -0.0000

Data Index: 650863 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.6987. Min Act: -0.0000

Data Index: 592639 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.7284. Min Act: -0.0000

Data Index: 47909 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.6513. Min Act: -0.0000

Data Index: 377655 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.8170. Min Range: -0.8170

Max Act: 0.6127. Min Act: -0.0000

Data Index: 254809 (C4 (Web Text))

Max Activating Token Index: 235