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

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

Neuron 1839 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3657. Min Act: -0.0003

Data Index: 826046 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3551. Min Act: -0.0003

Data Index: 1084479 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3257. Min Act: -0.0003

Data Index: 449424 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2294. Min Act: -0.0003

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2168. Min Act: -0.0003

Data Index: 1144584 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1863. Min Act: -0.0003

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1866. Min Act: -0.0003

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1791. Min Act: -0.0003

Data Index: 432261 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1881. Min Act: -0.0003

Data Index: 905622 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1881. Min Act: -0.0003

Data Index: 651451 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1937. Min Act: -0.0003

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1752. Min Act: -0.0003

Data Index: 331124 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1724. Min Act: -0.0003

Data Index: 270288 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1727. Min Act: -0.0003

Data Index: 340624 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1719. Min Act: -0.0003

Data Index: 88256 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1682. Min Act: -0.0003

Data Index: 474136 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1675. Min Act: -0.0003

Data Index: 680070 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1600. Min Act: -0.0003

Data Index: 1075740 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1720. Min Act: -0.0003

Data Index: 694606 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.1644. Min Act: -0.0003

Data Index: 754643 (C4 (Web Text))

Max Activating Token Index: 444