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

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

Neuron 1816 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.5843. Min Act: -0.0000

Data Index: 856944 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.4256. Min Act: -0.0000

Data Index: 749555 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.3855. Min Act: -0.0000

Data Index: 538216 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.3651. Min Act: -0.0000

Data Index: 963812 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.3376. Min Act: -0.0000

Data Index: 444718 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.3995. Min Act: -0.0000

Data Index: 1344581 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1742. Min Act: -0.0000

Data Index: 508915 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.2349. Min Act: -0.0000

Data Index: 899506 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1638. Min Act: -0.0000

Data Index: 482148 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1117991 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1674. Min Act: -0.0000

Data Index: 612913 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1028. Min Act: -0.0000

Data Index: 104753 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1192515 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1216897 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0831. Min Act: -0.0000

Data Index: 90597 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1116104 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1083311 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1041345 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0095. Min Act: -0.0000

Data Index: 870979 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9827. Min Act: -0.0000

Data Index: 193278 (C4 (Web Text))

Max Activating Token Index: 533