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

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

Neuron 299 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.8551. Min Act: -0.0000

Data Index: 577772 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7645. Min Act: -0.0000

Data Index: 72682 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1216797 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1357868 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6027. Min Act: -0.0000

Data Index: 584142 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5186. Min Act: -0.0000

Data Index: 749573 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1128993 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4859. Min Act: -0.0000

Data Index: 655519 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5012. Min Act: -0.0000

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5200. Min Act: -0.0000

Data Index: 851938 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1011813 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5061. Min Act: -0.0000

Data Index: 279579 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4463. Min Act: -0.0000

Data Index: 607222 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4816. Min Act: -0.0000

Data Index: 404628 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1031068 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1014698 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4202. Min Act: -0.0000

Data Index: 954752 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1092813 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1304617 (C4 (Web Text))

Max Activating Token Index: 269