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

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

Neuron 3162 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.7325. Min Act: -0.0000

Data Index: 1623463 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.4726. Min Act: -0.0000

Data Index: 1384390 (Python Code)

Max Activating Token Index: 177

Text #2

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.3001. Min Act: -0.0000

Data Index: 1133949 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.1990. Min Act: -0.0000

Data Index: 214090 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.2689. Min Act: -0.0000

Data Index: 1628181 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.2166. Min Act: -0.0000

Data Index: 1071880 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1314679 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.1477. Min Act: -0.0000

Data Index: 1414801 (Python Code)

Max Activating Token Index: 708

Text #8

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.2031. Min Act: -0.0000

Data Index: 1606381 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.1775. Min Act: -0.0000

Data Index: 1514789 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.0655. Min Act: -0.0000

Data Index: 1628795 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.2307. Min Act: -0.0000

Data Index: 1545682 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.1567. Min Act: -0.0000

Data Index: 296709 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.1333. Min Act: -0.0000

Data Index: 918073 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.0254. Min Act: -0.0000

Data Index: 705910 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.2413. Min Act: -0.0000

Data Index: 61973 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 2.7325. Min Range: -2.7325

Max Act: 2.2728. Min Act: -0.0000

Data Index: 1524995 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 2.7325. Min Range: -2.7325

Max Act: 1.9087. Min Act: -0.0000

Data Index: 1376686 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 2.7325. Min Range: -2.7325

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1618493 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 2.7325. Min Range: -2.7325

Max Act: 1.9902. Min Act: -0.0000

Data Index: 1568464 (Python Code)

Max Activating Token Index: 28