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

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

Neuron 2172 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: 1.7788. Min Range: -1.7788

Max Act: 1.7788. Min Act: -0.0000

Data Index: 556641 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.3759. Min Act: -0.0000

Data Index: 402250 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1033947 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.3631. Min Act: -0.0000

Data Index: 360819 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.3206. Min Act: -0.0000

Data Index: 601676 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2135. Min Act: -0.0000

Data Index: 853873 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2788. Min Act: -0.0000

Data Index: 431608 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1591. Min Act: -0.0000

Data Index: 420743 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1582. Min Act: -0.0000

Data Index: 997805 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1264968 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1006151 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1901. Min Act: -0.0000

Data Index: 725463 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0950. Min Act: -0.0000

Data Index: 588569 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1323189 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0985. Min Act: -0.0000

Data Index: 153400 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1222010 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0827. Min Act: -0.0000

Data Index: 197801 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0075. Min Act: -0.0000

Data Index: 412419 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0229. Min Act: -0.0000

Data Index: 135722 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0388. Min Act: -0.0001

Data Index: 73237 (C4 (Web Text))

Max Activating Token Index: 939