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

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

Neuron 2054 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4623. Min Act: -0.0001

Data Index: 367762 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.7653. Min Act: -0.0000

Data Index: 1340527 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.7887. Min Act: -0.0001

Data Index: 503451 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5792. Min Act: -0.0001

Data Index: 886857 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.6794. Min Act: -0.0001

Data Index: 618717 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4903. Min Act: -0.0001

Data Index: 849692 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.1947. Min Act: -0.0001

Data Index: 204082 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4301. Min Act: -0.0001

Data Index: 283832 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.2486. Min Act: -0.0001

Data Index: 1059609 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.3874. Min Act: -0.0001

Data Index: 962304 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.3567. Min Act: -0.0001

Data Index: 112287 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.2190. Min Act: -0.0001

Data Index: 468803 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4979. Min Act: -0.0001

Data Index: 801417 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4895. Min Act: -0.0001

Data Index: 719526 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4937. Min Act: -0.0001

Data Index: 732353 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.3386. Min Act: -0.0001

Data Index: 782368 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4740. Min Act: -0.0001

Data Index: 1106961 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4774. Min Act: -0.0001

Data Index: 483625 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.4506. Min Act: -0.0001

Data Index: 1081149 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5814. Min Act: -0.0001

Data Index: 445815 (C4 (Web Text))

Max Activating Token Index: 779