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

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

Neuron 3217 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0000

Data Index: 235809 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2257. Min Act: -0.0000

Data Index: 762647 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2130. Min Act: -0.0000

Data Index: 718034 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2086. Min Act: -0.0000

Data Index: 165247 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2049. Min Act: -0.0000

Data Index: 66590 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1839. Min Act: -0.0000

Data Index: 603441 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1847. Min Act: -0.0000

Data Index: 101087 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1889. Min Act: -0.0000

Data Index: 757318 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1810. Min Act: -0.0000

Data Index: 93033 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1842. Min Act: -0.0000

Data Index: 907858 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1747. Min Act: -0.0000

Data Index: 515457 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1942. Min Act: -0.0000

Data Index: 56697 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1803. Min Act: -0.0000

Data Index: 649787 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1855. Min Act: -0.0000

Data Index: 19545 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1776. Min Act: -0.0000

Data Index: 212559 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1761. Min Act: -0.0000

Data Index: 589292 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1735. Min Act: -0.0000

Data Index: 118403 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1877. Min Act: -0.0000

Data Index: 653637 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1340450 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1799. Min Act: -0.0000

Data Index: 430529 (C4 (Web Text))

Max Activating Token Index: 504