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

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

Neuron 2575 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: 0.2300. Min Range: -0.2300

Max Act: 0.2300. Min Act: -0.0002

Data Index: 104861 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1757. Min Act: -0.0001

Data Index: 200855 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1726. Min Act: -0.0002

Data Index: 1097602 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1719. Min Act: -0.0002

Data Index: 1197862 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1603. Min Act: -0.0002

Data Index: 1146742 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1758. Min Act: -0.0001

Data Index: 781624 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1528. Min Act: -0.0002

Data Index: 44591 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1738. Min Act: -0.0002

Data Index: 113448 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1723. Min Act: -0.0002

Data Index: 965958 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1614. Min Act: -0.0001

Data Index: 30925 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1024753 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1551. Min Act: -0.0001

Data Index: 749966 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1657. Min Act: -0.0002

Data Index: 1193862 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1708. Min Act: -0.0002

Data Index: 1259421 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1415. Min Act: -0.0002

Data Index: 332304 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1483. Min Act: -0.0001

Data Index: 821392 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1739. Min Act: -0.0002

Data Index: 836424 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1613. Min Act: -0.0002

Data Index: 1094271 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1525. Min Act: -0.0002

Data Index: 608351 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1661. Min Act: -0.0002

Data Index: 155663 (C4 (Web Text))

Max Activating Token Index: 171