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

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

Neuron 2463 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1446861 (Python Code)

Max Activating Token Index: 910

Text #1

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2281. Min Act: -0.0000

Data Index: 324234 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2201. Min Act: -0.0000

Data Index: 87835 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1431141 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1878. Min Act: -0.0000

Data Index: 85553 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1270325 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1940. Min Act: -0.0000

Data Index: 20038 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1051356 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1765. Min Act: -0.0000

Data Index: 60730 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1805. Min Act: -0.0000

Data Index: 802195 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1901. Min Act: -0.0000

Data Index: 9437 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1098006 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1092561 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1787. Min Act: -0.0000

Data Index: 485419 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1706. Min Act: -0.0000

Data Index: 514858 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1761. Min Act: -0.0000

Data Index: 690275 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1762. Min Act: -0.0000

Data Index: 513304 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1751. Min Act: -0.0000

Data Index: 621628 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1738. Min Act: -0.0000

Data Index: 50968 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1334033 (C4 (Web Text))

Max Activating Token Index: 277