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

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

Neuron 574 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: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0000

Data Index: 796846 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1717. Min Act: -0.0000

Data Index: 179210 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1752. Min Act: -0.0000

Data Index: 993685 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1079977 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1647. Min Act: -0.0001

Data Index: 215868 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1647. Min Act: -0.0000

Data Index: 902407 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1586. Min Act: 0.0000

Data Index: 9165 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1568. Min Act: -0.0000

Data Index: 293550 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1683. Min Act: -0.0000

Data Index: 367821 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1572. Min Act: -0.0000

Data Index: 846343 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1533. Min Act: 0.0000

Data Index: 949318 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1542. Min Act: -0.0000

Data Index: 489242 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1551. Min Act: -0.0001

Data Index: 916090 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1080972 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1519. Min Act: -0.0001

Data Index: 503055 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1534. Min Act: -0.0000

Data Index: 492624 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1528. Min Act: -0.0000

Data Index: 925846 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1535. Min Act: -0.0001

Data Index: 40386 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1176891 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1514. Min Act: -0.0001

Data Index: 1343894 (C4 (Web Text))

Max Activating Token Index: 1012