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

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

Neuron 3059 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2503. Min Range: -3.2503

Max Act: 3.2503. Min Act: -0.0000

Data Index: 1040548 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 3.2503. Min Range: -3.2503

Max Act: 3.0934. Min Act: -0.0000

Data Index: 1099406 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.9482. Min Act: -0.0000

Data Index: 638889 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.5765. Min Act: -0.0000

Data Index: 255810 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 3.2503. Min Range: -3.2503

Max Act: 3.0356. Min Act: -0.0001

Data Index: 937426 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.9378. Min Act: -0.0000

Data Index: 394154 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.5354. Min Act: -0.0000

Data Index: 561079 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.6528. Min Act: -0.0001

Data Index: 1276764 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.5972. Min Act: -0.0001

Data Index: 149797 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.4847. Min Act: -0.0001

Data Index: 772621 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.4102. Min Act: -0.0000

Data Index: 1000746 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.6158. Min Act: -0.0000

Data Index: 1264007 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.6389. Min Act: -0.0001

Data Index: 845201 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.4751. Min Act: -0.0000

Data Index: 1219666 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.4772. Min Act: -0.0001

Data Index: 1072370 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.7488. Min Act: -0.0001

Data Index: 374922 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.5869. Min Act: -0.0000

Data Index: 1148906 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.7318. Min Act: -0.0001

Data Index: 826881 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.3959. Min Act: -0.0001

Data Index: 1061563 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.2503. Min Range: -3.2503

Max Act: 2.2299. Min Act: -0.0000

Data Index: 204755 (C4 (Web Text))

Max Activating Token Index: 742