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

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

Neuron 4375 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6710. Min Act: -0.0000

Data Index: 655486 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5750. Min Act: -0.0000

Data Index: 589395 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5349. Min Act: -0.0000

Data Index: 406233 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4710. Min Act: -0.0000

Data Index: 846321 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4654. Min Act: -0.0000

Data Index: 647690 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4093. Min Act: -0.0000

Data Index: 381874 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4311. Min Act: -0.0000

Data Index: 633883 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1453634 (Python Code)

Max Activating Token Index: 268

Text #9

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3939. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3643. Min Act: -0.0000

Data Index: 871398 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1325883 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3649. Min Act: -0.0000

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3513. Min Act: -0.0000

Data Index: 601956 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3716. Min Act: -0.0000

Data Index: 97278 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1327215 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1323427 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3577. Min Act: -0.0000

Data Index: 961318 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3336. Min Act: -0.0000

Data Index: 956554 (C4 (Web Text))

Max Activating Token Index: 710