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

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

Neuron 522 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: 4.8390. Min Range: -4.8390

Max Act: 4.8390. Min Act: -0.0000

Data Index: 388742 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 4.8390. Min Range: -4.8390

Max Act: 4.1889. Min Act: -0.0000

Data Index: 73996 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.7284. Min Act: -0.0000

Data Index: 87347 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.5209. Min Act: -0.0000

Data Index: 784867 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.3628. Min Act: -0.0000

Data Index: 1185438 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.5149. Min Act: -0.0000

Data Index: 421702 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.7425. Min Act: -0.0000

Data Index: 319925 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.3077. Min Act: -0.0000

Data Index: 854661 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.1023. Min Act: -0.0000

Data Index: 539969 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.2381. Min Act: -0.0000

Data Index: 1321773 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.0800. Min Act: -0.0000

Data Index: 371558 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.2134. Min Act: -0.0000

Data Index: 1053192 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.0404. Min Act: -0.0000

Data Index: 128503 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.0781. Min Act: -0.0000

Data Index: 433029 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.0303. Min Act: -0.0000

Data Index: 860436 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.0168. Min Act: -0.0000

Data Index: 627759 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 4.8390. Min Range: -4.8390

Max Act: 2.7457. Min Act: -0.0000

Data Index: 409570 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 4.8390. Min Range: -4.8390

Max Act: 2.9989. Min Act: -0.0000

Data Index: 1069098 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 4.8390. Min Range: -4.8390

Max Act: 3.1038. Min Act: -0.0000

Data Index: 916413 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 4.8390. Min Range: -4.8390

Max Act: 2.9621. Min Act: -0.0000

Data Index: 49346 (C4 (Web Text))

Max Activating Token Index: 712