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

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

Neuron 423 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1964. Min Act: -0.0002

Data Index: 1254060 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2046. Min Act: -0.0002

Data Index: 704671 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0002

Data Index: 438999 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1919. Min Act: -0.0002

Data Index: 416668 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1824. Min Act: -0.0002

Data Index: 319630 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2190. Min Act: -0.0002

Data Index: 979452 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1944. Min Act: -0.0002

Data Index: 384779 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2028. Min Act: -0.0002

Data Index: 860397 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1919. Min Act: -0.0003

Data Index: 805291 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1838. Min Act: -0.0002

Data Index: 949292 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1718. Min Act: -0.0002

Data Index: 226057 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1756. Min Act: -0.0002

Data Index: 23743 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2260. Min Act: -0.0002

Data Index: 1135891 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1846. Min Act: -0.0002

Data Index: 540781 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1886. Min Act: -0.0002

Data Index: 1000067 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1755. Min Act: -0.0002

Data Index: 1172583 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1809. Min Act: -0.0002

Data Index: 296319 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1754. Min Act: -0.0002

Data Index: 1351429 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1836. Min Act: -0.0002

Data Index: 1182483 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1518. Min Act: -0.0002

Data Index: 315019 (C4 (Web Text))

Max Activating Token Index: 971