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

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

Neuron 5254 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: 1.7778. Min Range: -1.7778

Max Act: 1.7778. Min Act: -0.0000

Data Index: 602088 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4558. Min Act: -0.0000

Data Index: 347217 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.6380. Min Act: -0.0000

Data Index: 579198 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.5082. Min Act: -0.0000

Data Index: 596347 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1174484 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3180. Min Act: -0.0000

Data Index: 748586 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3149. Min Act: -0.0000

Data Index: 637481 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3356. Min Act: -0.0000

Data Index: 396157 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4118. Min Act: -0.0000

Data Index: 429500 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2564. Min Act: -0.0000

Data Index: 807895 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3345. Min Act: -0.0000

Data Index: 71580 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2478. Min Act: -0.0000

Data Index: 329991 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3305. Min Act: -0.0000

Data Index: 985 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1278594 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2268. Min Act: -0.0000

Data Index: 308430 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.1868. Min Act: -0.0000

Data Index: 397017 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.1376. Min Act: -0.0000

Data Index: 761130 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1292482 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2843. Min Act: -0.0000

Data Index: 739336 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.1886. Min Act: -0.0000

Data Index: 810400 (C4 (Web Text))

Max Activating Token Index: 37