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

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

Neuron 4133 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1240807 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6932. Min Act: -0.0000

Data Index: 665414 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6764. Min Act: -0.0000

Data Index: 542978 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6177. Min Act: -0.0000

Data Index: 418584 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6327. Min Act: -0.0000

Data Index: 939301 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6010. Min Act: -0.0000

Data Index: 623772 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6015. Min Act: -0.0000

Data Index: 784367 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5712. Min Act: -0.0000

Data Index: 455670 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5093. Min Act: -0.0000

Data Index: 740156 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5722. Min Act: -0.0000

Data Index: 351588 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5373. Min Act: -0.0000

Data Index: 86454 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5271. Min Act: -0.0000

Data Index: 551655 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.4881. Min Act: -0.0000

Data Index: 971322 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.4877. Min Act: -0.0000

Data Index: 629419 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5364. Min Act: -0.0000

Data Index: 609587 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1149542 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1336166 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.4792. Min Act: -0.0000

Data Index: 975193 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.4636. Min Act: -0.0000

Data Index: 565769 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.4736. Min Act: -0.0000

Data Index: 764822 (C4 (Web Text))

Max Activating Token Index: 795