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

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

Neuron 2329 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1526. Min Range: -2.1526

Max Act: 2.1526. Min Act: -0.0000

Data Index: 722818 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 2.1526. Min Range: -2.1526

Max Act: 2.0088. Min Act: -0.0000

Data Index: 1258411 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 2.1526. Min Range: -2.1526

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1228038 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.9275. Min Act: -0.0000

Data Index: 94602 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.7689. Min Act: -0.0000

Data Index: 747675 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.9016. Min Act: -0.0000

Data Index: 29296 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.8686. Min Act: -0.0000

Data Index: 871089 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.8392. Min Act: -0.0000

Data Index: 1206877 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.6483. Min Act: -0.0000

Data Index: 1370624 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1591255 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1378381 (Python Code)

Max Activating Token Index: 759

Text #11

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1595135 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.5650. Min Act: -0.0000

Data Index: 1496520 (Python Code)

Max Activating Token Index: 119

Text #13

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1481908 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1453273 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1394149 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1156213 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.5637. Min Act: -0.0000

Data Index: 1652840 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1041663 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 2.1526. Min Range: -2.1526

Max Act: 1.4868. Min Act: -0.0000

Data Index: 307494 (C4 (Web Text))

Max Activating Token Index: 572