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

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

Neuron 3898 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: 0.1849. Min Range: -0.1849

Max Act: 0.1787. Min Act: -0.0001

Data Index: 691998 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1772. Min Act: -0.0001

Data Index: 611879 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1477. Min Act: -0.0001

Data Index: 837307 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1705. Min Act: -0.0001

Data Index: 554859 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1112029 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0001

Data Index: 186596 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1625. Min Act: -0.0001

Data Index: 194209 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1698. Min Act: -0.0001

Data Index: 966809 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1480. Min Act: -0.0001

Data Index: 245695 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1570. Min Act: -0.0001

Data Index: 206871 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1489. Min Act: -0.0002

Data Index: 870642 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1721. Min Act: -0.0001

Data Index: 312736 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1648. Min Act: -0.0002

Data Index: 1574136 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1482506 (Python Code)

Max Activating Token Index: 815

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1513. Min Act: -0.0001

Data Index: 996466 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1481941 (Python Code)

Max Activating Token Index: 271

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1473. Min Act: -0.0001

Data Index: 900551 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1579461 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1482914 (Python Code)

Max Activating Token Index: 722

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1436169 (Python Code)

Max Activating Token Index: 229