Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 486 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1288883 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1149932 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1029969 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1981. Min Act: -0.0001

Data Index: 474101 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2059. Min Act: -0.0001

Data Index: 819523 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1130639 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1874. Min Act: -0.0001

Data Index: 76530 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1087836 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1147494 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1230560 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1739. Min Act: -0.0001

Data Index: 842837 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1794. Min Act: -0.0001

Data Index: 787104 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1665. Min Act: -0.0001

Data Index: 774921 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1657. Min Act: -0.0001

Data Index: 767564 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1718. Min Act: -0.0001

Data Index: 111032 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1859. Min Act: -0.0001

Data Index: 703764 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1690. Min Act: -0.0001

Data Index: 256497 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1063353 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1557. Min Act: -0.0001

Data Index: 184464 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1581. Min Act: -0.0001

Data Index: 441634 (C4 (Web Text))

Max Activating Token Index: 301