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

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

Neuron 3131 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2419. Min Act: -0.0000

Data Index: 329606 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2189. Min Act: -0.0000

Data Index: 780464 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2260. Min Act: -0.0000

Data Index: 236426 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1264206 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1090871 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1696. Min Act: -0.0000

Data Index: 821099 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1121041 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1880. Min Act: -0.0000

Data Index: 249670 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1670. Min Act: -0.0000

Data Index: 941861 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1673. Min Act: -0.0000

Data Index: 466859 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1674. Min Act: -0.0000

Data Index: 80285 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1225687 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1740. Min Act: -0.0000

Data Index: 604928 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1604. Min Act: -0.0000

Data Index: 541218 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1562. Min Act: -0.0000

Data Index: 392350 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1543. Min Act: -0.0000

Data Index: 143901 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1506. Min Act: -0.0000

Data Index: 526133 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1493. Min Act: -0.0000

Data Index: 428882 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1482. Min Act: -0.0000

Data Index: 624860 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1511. Min Act: -0.0000

Data Index: 440610 (C4 (Web Text))

Max Activating Token Index: 307