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

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

Neuron 1700 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.9774. Min Act: -0.0001

Data Index: 1367617 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8697. Min Act: -0.0001

Data Index: 1450257 (Python Code)

Max Activating Token Index: 739

Text #2

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7743. Min Act: -0.0001

Data Index: 1381660 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7478. Min Act: -0.0001

Data Index: 1630401 (Python Code)

Max Activating Token Index: 814

Text #4

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1493234 (Python Code)

Max Activating Token Index: 226

Text #5

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1404545 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7368. Min Act: -0.0001

Data Index: 1498391 (Python Code)

Max Activating Token Index: 696

Text #7

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1627587 (Python Code)

Max Activating Token Index: 277

Text #8

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7427. Min Act: -0.0001

Data Index: 1465643 (Python Code)

Max Activating Token Index: 725

Text #9

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1416059 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1571985 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6603. Min Act: -0.0001

Data Index: 1566676 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6576. Min Act: -0.0001

Data Index: 1648514 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1611716 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6791. Min Act: -0.0001

Data Index: 1518790 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7005. Min Act: -0.0001

Data Index: 1548703 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6487. Min Act: -0.0001

Data Index: 1468093 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6730. Min Act: -0.0001

Data Index: 1525607 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6904. Min Act: -0.0001

Data Index: 1563753 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6471. Min Act: -0.0001

Data Index: 1653774 (Python Code)

Max Activating Token Index: 1021