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

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

Neuron 3219 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: 0.1079. Min Range: -0.1079

Max Act: 0.1079. Min Act: -0.0002

Data Index: 153756 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1289382 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0895. Min Act: -0.0002

Data Index: 881198 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1164109 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0892. Min Act: -0.0002

Data Index: 575022 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0845. Min Act: -0.0002

Data Index: 286271 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0844. Min Act: -0.0002

Data Index: 707417 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0799. Min Act: -0.0002

Data Index: 489753 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1097825 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0899. Min Act: -0.0002

Data Index: 461712 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0824. Min Act: -0.0002

Data Index: 283203 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0833. Min Act: -0.0002

Data Index: 942502 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0836. Min Act: -0.0002

Data Index: 810900 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0797. Min Act: -0.0002

Data Index: 886071 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0799. Min Act: -0.0002

Data Index: 990847 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0822. Min Act: -0.0002

Data Index: 810091 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0737. Min Act: -0.0002

Data Index: 135990 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0779. Min Act: -0.0002

Data Index: 743476 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0841. Min Act: -0.0002

Data Index: 743222 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0809. Min Act: -0.0002

Data Index: 14985 (C4 (Web Text))

Max Activating Token Index: 97