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

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

Neuron 1060 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.7259. Min Act: -0.0000

Data Index: 426504 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6283. Min Act: -0.0000

Data Index: 742331 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1096328 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5941. Min Act: -0.0000

Data Index: 246037 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1102089 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1026264 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5922. Min Act: -0.0000

Data Index: 730577 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5947. Min Act: -0.0001

Data Index: 564175 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1084286 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1000909 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5656. Min Act: -0.0000

Data Index: 94067 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5797. Min Act: -0.0000

Data Index: 722042 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1356792 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5539. Min Act: -0.0000

Data Index: 33740 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5563. Min Act: -0.0000

Data Index: 879129 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5723. Min Act: -0.0000

Data Index: 954873 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5625. Min Act: -0.0000

Data Index: 246594 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1007759 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5696. Min Act: -0.0000

Data Index: 587791 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5292. Min Act: -0.0001

Data Index: 1015557 (C4 (Web Text))

Max Activating Token Index: 754