Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4952 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0001

Data Index: 781519 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1285064 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2118. Min Act: -0.0001

Data Index: 142829 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1003287 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1665. Min Act: -0.0001

Data Index: 479936 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1653. Min Act: -0.0001

Data Index: 353272 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1628. Min Act: -0.0001

Data Index: 954884 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1846. Min Act: -0.0001

Data Index: 213946 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1632. Min Act: -0.0001

Data Index: 696868 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1673. Min Act: -0.0001

Data Index: 640433 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1577. Min Act: -0.0001

Data Index: 689578 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1560. Min Act: -0.0001

Data Index: 26766 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1211224 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1498. Min Act: -0.0001

Data Index: 956435 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1540. Min Act: -0.0001

Data Index: 704156 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1461. Min Act: -0.0001

Data Index: 797906 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1511. Min Act: -0.0001

Data Index: 789818 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1469. Min Act: -0.0001

Data Index: 100417 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1442. Min Act: -0.0001

Data Index: 127420 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1442. Min Act: -0.0001

Data Index: 143916 (C4 (Web Text))

Max Activating Token Index: 106