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

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

Neuron 3681 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6595. Min Act: -0.0001

Data Index: 1229234 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5905. Min Act: -0.0001

Data Index: 1174908 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5101. Min Act: -0.0001

Data Index: 21367 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5320. Min Act: -0.0001

Data Index: 964347 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5266. Min Act: -0.0001

Data Index: 815814 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4980. Min Act: -0.0001

Data Index: 857035 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4731. Min Act: -0.0001

Data Index: 711900 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4617. Min Act: -0.0001

Data Index: 415312 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4716. Min Act: -0.0001

Data Index: 441457 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4283. Min Act: -0.0001

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4355. Min Act: -0.0001

Data Index: 1268207 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3924. Min Act: -0.0001

Data Index: 872813 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4415. Min Act: -0.0001

Data Index: 124237 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4095. Min Act: -0.0001

Data Index: 775899 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4447. Min Act: -0.0001

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3761. Min Act: -0.0001

Data Index: 510776 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4262. Min Act: -0.0001

Data Index: 10201 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3948. Min Act: -0.0001

Data Index: 328486 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4330. Min Act: -0.0001

Data Index: 325552 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1150730 (C4 (Web Text))

Max Activating Token Index: 898