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

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

Neuron 920 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: 0.6681. Min Range: -0.6681

Max Act: 0.6681. Min Act: -0.0000

Data Index: 721913 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1120019 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4823. Min Act: -0.0000

Data Index: 477865 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4776. Min Act: -0.0000

Data Index: 81038 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1284623 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4687. Min Act: -0.0000

Data Index: 591048 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1019713 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1242942 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4575. Min Act: -0.0000

Data Index: 211236 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4310. Min Act: -0.0000

Data Index: 652448 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4070. Min Act: -0.0000

Data Index: 871268 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4070. Min Act: -0.0000

Data Index: 523110 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4196. Min Act: -0.0000

Data Index: 410461 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4259. Min Act: -0.0000

Data Index: 361687 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4101. Min Act: -0.0000

Data Index: 62447 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1161423 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4188. Min Act: -0.0000

Data Index: 39944 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1055361 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.3974. Min Act: -0.0000

Data Index: 693170 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1058767 (C4 (Web Text))

Max Activating Token Index: 924