Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3278 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1296521 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1231392 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5398. Min Act: -0.0000

Data Index: 761391 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1348226 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5466. Min Act: -0.0000

Data Index: 439280 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5418. Min Act: -0.0000

Data Index: 389843 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5229. Min Act: -0.0000

Data Index: 898031 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1163807 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4940. Min Act: -0.0000

Data Index: 987932 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5065. Min Act: -0.0000

Data Index: 484381 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1139237 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5227. Min Act: -0.0000

Data Index: 577884 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4991. Min Act: -0.0000

Data Index: 49418 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4959. Min Act: -0.0000

Data Index: 395165 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5216. Min Act: -0.0000

Data Index: 609528 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4698. Min Act: -0.0000

Data Index: 563903 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4716. Min Act: -0.0000

Data Index: 499765 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4772. Min Act: -0.0000

Data Index: 361396 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4747. Min Act: -0.0000

Data Index: 298215 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4883. Min Act: -0.0000

Data Index: 679775 (C4 (Web Text))

Max Activating Token Index: 89