Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5138 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1838. Min Act: -0.0002

Data Index: 1354263 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1842. Min Act: -0.0002

Data Index: 1177337 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1825. Min Act: -0.0002

Data Index: 1311258 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1762. Min Act: -0.0002

Data Index: 1239664 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1726. Min Act: -0.0002

Data Index: 443437 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1751. Min Act: -0.0002

Data Index: 593274 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1703. Min Act: -0.0002

Data Index: 809177 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1750. Min Act: -0.0002

Data Index: 262619 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1704. Min Act: -0.0002

Data Index: 974981 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1772. Min Act: -0.0002

Data Index: 1213599 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1735. Min Act: -0.0002

Data Index: 988182 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1719. Min Act: -0.0002

Data Index: 753380 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1690. Min Act: -0.0002

Data Index: 260603 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1693. Min Act: -0.0002

Data Index: 58324 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1712. Min Act: -0.0002

Data Index: 561000 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1697. Min Act: -0.0002

Data Index: 445389 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1676. Min Act: -0.0002

Data Index: 235285 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1658. Min Act: -0.0002

Data Index: 1009588 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1698. Min Act: -0.0002

Data Index: 914007 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1650. Min Act: -0.0002

Data Index: 718116 (C4 (Web Text))

Max Activating Token Index: 309