Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1333 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1332792 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7491. Min Act: -0.0000

Data Index: 22032 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6918. Min Act: -0.0000

Data Index: 19333 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6354. Min Act: -0.0000

Data Index: 110105 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5968. Min Act: -0.0000

Data Index: 127880 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1295037 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6044. Min Act: -0.0000

Data Index: 504495 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5852. Min Act: -0.0000

Data Index: 110488 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1304213 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5457. Min Act: -0.0000

Data Index: 747645 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5351. Min Act: -0.0000

Data Index: 954436 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1188177 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1185747 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5174. Min Act: -0.0000

Data Index: 484847 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5345. Min Act: -0.0000

Data Index: 517258 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5023. Min Act: -0.0000

Data Index: 127313 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4825. Min Act: -0.0000

Data Index: 201739 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5120. Min Act: -0.0000

Data Index: 803537 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5098. Min Act: -0.0000

Data Index: 884030 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5144. Min Act: -0.0000

Data Index: 572619 (C4 (Web Text))

Max Activating Token Index: 1013