Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4050 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1826. Min Act: -0.0001

Data Index: 287180 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1856. Min Act: -0.0000

Data Index: 730245 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1766. Min Act: -0.0001

Data Index: 855884 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1672. Min Act: -0.0000

Data Index: 187687 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1606. Min Act: -0.0000

Data Index: 998515 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1242284 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1548. Min Act: -0.0001

Data Index: 660894 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1491. Min Act: -0.0001

Data Index: 327674 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1591. Min Act: -0.0000

Data Index: 543788 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1352769 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1509. Min Act: -0.0001

Data Index: 674500 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1598. Min Act: -0.0001

Data Index: 32761 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1007589 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1524. Min Act: -0.0000

Data Index: 907229 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1036518 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1450. Min Act: -0.0000

Data Index: 41170 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1396. Min Act: -0.0001

Data Index: 408977 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1433. Min Act: -0.0000

Data Index: 719125 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1430. Min Act: -0.0000

Data Index: 522371 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1365. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 280