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

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

Neuron 3862 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: 0.1851. Min Range: -0.1851

Max Act: 0.1840. Min Act: -0.0000

Data Index: 452301 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1329073 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1126059 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1778. Min Act: -0.0000

Data Index: 203459 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1675. Min Act: -0.0000

Data Index: 954707 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1586. Min Act: -0.0000

Data Index: 592034 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1100829 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1459. Min Act: -0.0000

Data Index: 170498 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1476. Min Act: -0.0000

Data Index: 175973 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1593555 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1390778 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1483. Min Act: -0.0000

Data Index: 121959 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1467. Min Act: -0.0000

Data Index: 389256 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1258538 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1502. Min Act: -0.0000

Data Index: 836346 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1428. Min Act: -0.0000

Data Index: 239897 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1270757 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1454. Min Act: -0.0000

Data Index: 838933 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1386407 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1440. Min Act: -0.0000

Data Index: 667584 (C4 (Web Text))

Max Activating Token Index: 110