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

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

Neuron 2582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.0224. Min Act: -0.0001

Data Index: 826515 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.0430. Min Act: -0.0001

Data Index: 180411 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.1580. Min Act: -0.0002

Data Index: 137487 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.0367. Min Act: -0.0002

Data Index: 771916 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.0504. Min Act: -0.0002

Data Index: 1340513 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.1881. Min Act: -0.0002

Data Index: 858721 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.8921. Min Act: -0.0001

Data Index: 230773 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.0352. Min Act: -0.0001

Data Index: 98995 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.8598. Min Act: -0.0002

Data Index: 827727 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.9982. Min Act: -0.0001

Data Index: 332802 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.1423. Min Act: -0.0001

Data Index: 589618 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.9456. Min Act: -0.0001

Data Index: 44308 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.8841. Min Act: -0.0001

Data Index: 405378 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.0835. Min Act: -0.0001

Data Index: 194332 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.9999. Min Act: -0.0001

Data Index: 152571 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 3.1881. Min Range: -3.1881

Max Act: 3.1009. Min Act: -0.0001

Data Index: 899856 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.7076. Min Act: -0.0002

Data Index: 1195272 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.9750. Min Act: -0.0002

Data Index: 358132 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.8704. Min Act: -0.0001

Data Index: 14182 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 3.1881. Min Range: -3.1881

Max Act: 2.8996. Min Act: -0.0002

Data Index: 605296 (C4 (Web Text))

Max Activating Token Index: 475