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

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

Neuron 2619 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1516178 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1460797 (Python Code)

Max Activating Token Index: 753

Text #2

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6582. Min Act: -0.0001

Data Index: 1379541 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6461. Min Act: -0.0001

Data Index: 1600857 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6120. Min Act: -0.0001

Data Index: 1426498 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1414101 (Python Code)

Max Activating Token Index: 883

Text #6

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5989. Min Act: -0.0001

Data Index: 1595595 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1520815 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5581. Min Act: -0.0001

Data Index: 1492872 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5835. Min Act: -0.0001

Data Index: 383600 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5809. Min Act: -0.0001

Data Index: 1429107 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5556. Min Act: -0.0001

Data Index: 1382470 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1532326 (Python Code)

Max Activating Token Index: 231

Text #13

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5293. Min Act: -0.0001

Data Index: 529978 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5794. Min Act: -0.0001

Data Index: 731071 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1390734 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1444897 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5790. Min Act: -0.0001

Data Index: 1611092 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5491. Min Act: -0.0001

Data Index: 1080939 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5883. Min Act: -0.0001

Data Index: 1516968 (Python Code)

Max Activating Token Index: 714