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

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

Neuron 1703 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1603181 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6385. Min Act: -0.0000

Data Index: 1388850 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1592735 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1541670 (Python Code)

Max Activating Token Index: 898

Text #4

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1369972 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.3395. Min Act: -0.0000

Data Index: 1378653 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1399800 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1582817 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1501233 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1490041 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.3019. Min Act: 0.0000

Data Index: 1540160 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1451174 (Python Code)

Max Activating Token Index: 933

Text #12

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1381444 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1644928 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1399252 (Python Code)

Max Activating Token Index: 576

Text #15

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1471928 (Python Code)

Max Activating Token Index: 718

Text #16

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2513. Min Act: -0.0000

Data Index: 70773 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2454. Min Act: -0.0000

Data Index: 611540 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1424. Min Act: 0.0000

Data Index: 1603870 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2967. Min Act: 0.0000

Data Index: 1433151 (Python Code)

Max Activating Token Index: 52