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

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

Neuron 1000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0002

Data Index: 492998 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1056116 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0648. Min Act: -0.0002

Data Index: 630312 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0643. Min Act: -0.0002

Data Index: 337582 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1342232 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0509. Min Act: -0.0002

Data Index: 369890 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1064001 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0627. Min Act: -0.0002

Data Index: 484075 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1052738 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1141420 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0560. Min Act: -0.0002

Data Index: 980391 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1217555 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0489. Min Act: -0.0002

Data Index: 973710 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1154723 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0546. Min Act: -0.0002

Data Index: 859649 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1218841 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0523. Min Act: -0.0002

Data Index: 125484 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1142087 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0462. Min Act: -0.0002

Data Index: 586441 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1265112 (C4 (Web Text))

Max Activating Token Index: 688