Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7106. Min Act: -0.0000

Data Index: 103254 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7545. Min Act: -0.0000

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6356. Min Act: -0.0000

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6887. Min Act: -0.0000

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6617. Min Act: -0.0000

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6766. Min Act: -0.0000

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6733. Min Act: -0.0000

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6056. Min Act: -0.0000

Data Index: 848529 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5846. Min Act: -0.0000

Data Index: 900528 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6991. Min Act: -0.0000

Data Index: 824168 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5891. Min Act: -0.0000

Data Index: 298343 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6235. Min Act: -0.0000

Data Index: 133200 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6011. Min Act: -0.0000

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5640. Min Act: -0.0000

Data Index: 780788 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5773. Min Act: -0.0000

Data Index: 767102 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3908. Min Act: -0.0000

Data Index: 945603 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3880. Min Act: -0.0000

Data Index: 68598 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3982. Min Act: -0.0000

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4044. Min Act: -0.0000

Data Index: 628771 (C4 (Web Text))

Max Activating Token Index: 36