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

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

Neuron 3795 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2832. Min Act: -0.0001

Data Index: 648308 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2387. Min Act: -0.0001

Data Index: 1238441 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2066. Min Act: -0.0001

Data Index: 871451 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1080530 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1898. Min Act: -0.0001

Data Index: 286575 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1641. Min Act: -0.0001

Data Index: 98174 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1038562 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1840. Min Act: -0.0001

Data Index: 560607 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1130184 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1602. Min Act: -0.0001

Data Index: 994046 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1126288 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1617. Min Act: -0.0001

Data Index: 394899 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1675. Min Act: -0.0001

Data Index: 532608 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1801. Min Act: -0.0001

Data Index: 496903 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1661. Min Act: -0.0001

Data Index: 820017 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1584. Min Act: -0.0001

Data Index: 251708 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1222516 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1292405 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1255896 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1488. Min Act: -0.0001

Data Index: 952033 (C4 (Web Text))

Max Activating Token Index: 535