Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4549 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7747. Min Act: -0.0000

Data Index: 364891 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8421. Min Act: 0.0000

Data Index: 1282870 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6909. Min Act: -0.0000

Data Index: 758469 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6666. Min Act: -0.0000

Data Index: 994483 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6392. Min Act: 0.0000

Data Index: 1124482 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6308. Min Act: -0.0000

Data Index: 550197 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5980. Min Act: 0.0001

Data Index: 191215 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5879. Min Act: 0.0000

Data Index: 335551 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1198340 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5996. Min Act: -0.0000

Data Index: 270457 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5502. Min Act: -0.0000

Data Index: 4190 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5935. Min Act: -0.0000

Data Index: 22851 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5893. Min Act: -0.0000

Data Index: 652696 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5845. Min Act: -0.0000

Data Index: 493540 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5506. Min Act: 0.0000

Data Index: 1095260 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1059992 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5780. Min Act: -0.0000

Data Index: 90520 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5344. Min Act: -0.0000

Data Index: 85902 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1038273 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5485. Min Act: -0.0000

Data Index: 666187 (C4 (Web Text))

Max Activating Token Index: 66