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

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

Neuron 1604 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: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0002

Data Index: 172600 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1016006 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0692. Min Act: -0.0002

Data Index: 502971 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0620. Min Act: -0.0002

Data Index: 20329 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1354028 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0601. Min Act: -0.0002

Data Index: 969457 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1238658 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0560. Min Act: -0.0002

Data Index: 510988 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0647. Min Act: -0.0002

Data Index: 221450 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1116413 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0647. Min Act: -0.0002

Data Index: 843383 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0702. Min Act: -0.0002

Data Index: 103722 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0650. Min Act: -0.0002

Data Index: 156936 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0618. Min Act: -0.0002

Data Index: 715028 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0586. Min Act: -0.0002

Data Index: 474260 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1106530 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1282773 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0649. Min Act: -0.0002

Data Index: 997579 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1170386 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0553. Min Act: -0.0002

Data Index: 813920 (C4 (Web Text))

Max Activating Token Index: 612