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

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

Neuron 2116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0000

Data Index: 977956 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1855. Min Act: -0.0001

Data Index: 1231129 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1758. Min Act: -0.0000

Data Index: 826012 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1782. Min Act: -0.0000

Data Index: 374501 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1752. Min Act: -0.0000

Data Index: 661993 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1357045 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1079198 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1765. Min Act: -0.0000

Data Index: 462806 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1750. Min Act: -0.0001

Data Index: 991775 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1655. Min Act: -0.0001

Data Index: 904008 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1000152 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1248357 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1087522 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1517. Min Act: -0.0001

Data Index: 256720 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1005281 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1120104 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1198420 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1545. Min Act: -0.0000

Data Index: 953073 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1486. Min Act: -0.0000

Data Index: 325380 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1526. Min Act: -0.0000

Data Index: 663135 (C4 (Web Text))

Max Activating Token Index: 363