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

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

Neuron 3288 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: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1109596 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1050120 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0776. Min Act: -0.0000

Data Index: 637716 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0780. Min Act: -0.0000

Data Index: 289395 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0700. Min Act: -0.0000

Data Index: 546766 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0696. Min Act: -0.0000

Data Index: 372361 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0653. Min Act: -0.0000

Data Index: 494177 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0618. Min Act: -0.0000

Data Index: 124892 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0524. Min Act: -0.0000

Data Index: 311804 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0642. Min Act: -0.0000

Data Index: 596903 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1308103 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0629. Min Act: -0.0000

Data Index: 291449 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0653. Min Act: -0.0000

Data Index: 52576 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0572. Min Act: -0.0000

Data Index: 734977 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0601. Min Act: -0.0000

Data Index: 148077 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1121507 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0556. Min Act: -0.0000

Data Index: 162317 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0573. Min Act: -0.0000

Data Index: 377028 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0589. Min Act: -0.0000

Data Index: 309002 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0569. Min Act: -0.0000

Data Index: 171684 (C4 (Web Text))

Max Activating Token Index: 475