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

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

Neuron 522 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1527139 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1508958 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1561239 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1517653 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1610161 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1472255 (Python Code)

Max Activating Token Index: 639

Text #6

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1653802 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1656423 (Python Code)

Max Activating Token Index: 964

Text #8

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.0369. Min Act: -0.0000

Data Index: 551215 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1653712 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1573710 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1526753 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1525006 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1379832 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1578073 (Python Code)

Max Activating Token Index: 913

Text #15

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1475383 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1413463 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1449717 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1390965 (Python Code)

Max Activating Token Index: 608

Text #19

Max Range: 1.5388. Min Range: -1.5388

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1451665 (Python Code)

Max Activating Token Index: 523