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

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

Neuron 1564 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: 1.7135. Min Range: -1.7135

Max Act: 1.7135. Min Act: -0.0000

Data Index: 832460 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.6745. Min Act: -0.0000

Data Index: 811194 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.6548. Min Act: -0.0000

Data Index: 208678 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1138293 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2623. Min Act: -0.0000

Data Index: 620761 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.4974. Min Act: -0.0000

Data Index: 278957 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3801. Min Act: -0.0000

Data Index: 906784 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3534. Min Act: -0.0000

Data Index: 916392 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3880. Min Act: -0.0000

Data Index: 962713 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1303271 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1174037 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1245100 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.4015. Min Act: -0.0000

Data Index: 588961 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.3468. Min Act: -0.0000

Data Index: 103953 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2845. Min Act: -0.0000

Data Index: 829810 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2912. Min Act: -0.0000

Data Index: 204884 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1156737 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2985. Min Act: -0.0000

Data Index: 879110 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2908. Min Act: -0.0000

Data Index: 238082 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.7135. Min Range: -1.7135

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1007235 (C4 (Web Text))

Max Activating Token Index: 627