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

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

Neuron 3005 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2061. Min Range: -3.2061

Max Act: 3.2061. Min Act: -0.0000

Data Index: 606818 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.2061. Min Range: -3.2061

Max Act: 3.1289. Min Act: -0.0001

Data Index: 415092 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 3.2061. Min Range: -3.2061

Max Act: 3.1274. Min Act: -0.0000

Data Index: 60456 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.8080. Min Act: -0.0000

Data Index: 1595764 (Python Code)

Max Activating Token Index: 378

Text #4

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.5846. Min Act: -0.0000

Data Index: 1352572 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.5382. Min Act: -0.0000

Data Index: 1635170 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.9040. Min Act: -0.0000

Data Index: 179386 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.4904. Min Act: -0.0000

Data Index: 195457 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.6921. Min Act: -0.0000

Data Index: 307577 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.1300. Min Act: -0.0000

Data Index: 419372 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.4877. Min Act: -0.0000

Data Index: 928494 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.3290. Min Act: -0.0000

Data Index: 1213945 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.3212. Min Act: -0.0000

Data Index: 1062078 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.3241. Min Act: -0.0000

Data Index: 1295599 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.7000. Min Act: -0.0000

Data Index: 964543 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.4353. Min Act: -0.0000

Data Index: 713504 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.5403. Min Act: -0.0000

Data Index: 539812 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.4286. Min Act: -0.0000

Data Index: 586488 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.5343. Min Act: -0.0000

Data Index: 886919 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 3.2061. Min Range: -3.2061

Max Act: 2.5119. Min Act: -0.0000

Data Index: 1178772 (C4 (Web Text))

Max Activating Token Index: 221