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

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

Neuron 112 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.5672. Min Act: -0.0000

Data Index: 462001 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4557. Min Act: -0.0000

Data Index: 197470 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4301. Min Act: -0.0000

Data Index: 693009 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4188. Min Act: -0.0000

Data Index: 12837 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3863. Min Act: -0.0000

Data Index: 873093 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4129. Min Act: -0.0000

Data Index: 243692 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3834. Min Act: -0.0001

Data Index: 556213 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3836. Min Act: -0.0000

Data Index: 289131 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1232072 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3466. Min Act: -0.0000

Data Index: 814491 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1217825 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1075799 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3451. Min Act: -0.0000

Data Index: 853736 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3658. Min Act: -0.0000

Data Index: 814484 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3307. Min Act: -0.0000

Data Index: 716430 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3622. Min Act: -0.0000

Data Index: 9072 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3400. Min Act: -0.0000

Data Index: 610127 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1313225 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3472. Min Act: -0.0000

Data Index: 567945 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3332. Min Act: -0.0000

Data Index: 195637 (C4 (Web Text))

Max Activating Token Index: 799