Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1733 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.2116. Min Act: -0.0004

Data Index: 645912 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1014. Min Act: -0.0003

Data Index: 1054536 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0750. Min Act: -0.0003

Data Index: 77472 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0565. Min Act: -0.0003

Data Index: 868934 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0578. Min Act: -0.0003

Data Index: 239522 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0572. Min Act: -0.0003

Data Index: 315672 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0450. Min Act: -0.0003

Data Index: 298114 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0339. Min Act: -0.0002

Data Index: 353226 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0348. Min Act: -0.0003

Data Index: 582401 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0319. Min Act: -0.0002

Data Index: 959924 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0331. Min Act: -0.0004

Data Index: 313889 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1410211 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0245. Min Act: -0.0003

Data Index: 801123 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1132288 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0286. Min Act: -0.0004

Data Index: 1087076 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0310. Min Act: -0.0003

Data Index: 994014 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0327. Min Act: -0.0003

Data Index: 959918 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1158149 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0307. Min Act: -0.0004

Data Index: 790164 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.0311. Min Act: -0.0002

Data Index: 461595 (C4 (Web Text))

Max Activating Token Index: 81