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

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

Neuron 2262 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2449. Min Act: -0.0000

Data Index: 106341 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1301762 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1900. Min Act: -0.0000

Data Index: 670383 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1885. Min Act: -0.0000

Data Index: 906045 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1829. Min Act: -0.0000

Data Index: 502317 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1253469 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1727. Min Act: -0.0000

Data Index: 83909 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1617. Min Act: -0.0000

Data Index: 362564 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1356154 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1685. Min Act: -0.0000

Data Index: 981641 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1051145 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1717. Min Act: -0.0001

Data Index: 568140 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1650. Min Act: -0.0000

Data Index: 722576 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1641. Min Act: -0.0000

Data Index: 982839 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1530. Min Act: -0.0001

Data Index: 983396 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1468. Min Act: -0.0000

Data Index: 104870 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1513. Min Act: -0.0000

Data Index: 620114 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1024166 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1491. Min Act: -0.0000

Data Index: 432204 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1277736 (C4 (Web Text))

Max Activating Token Index: 833