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

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

Neuron 4956 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.9029. Min Act: -0.0000

Data Index: 442493 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.9036. Min Act: -0.0000

Data Index: 775789 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8764. Min Act: -0.0000

Data Index: 128753 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.8502. Min Act: -0.0000

Data Index: 915822 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.7636. Min Act: -0.0000

Data Index: 551525 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.6834. Min Act: -0.0000

Data Index: 517928 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.6959. Min Act: -0.0000

Data Index: 152506 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1315107 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.6373. Min Act: -0.0000

Data Index: 716389 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1469341 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5891. Min Act: -0.0000

Data Index: 144247 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5871. Min Act: -0.0000

Data Index: 740840 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1496054 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5436. Min Act: -0.0000

Data Index: 680159 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5707. Min Act: -0.0000

Data Index: 659268 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5552. Min Act: -0.0000

Data Index: 325574 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1113673 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.4687. Min Act: -0.0000

Data Index: 979463 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5506. Min Act: -0.0000

Data Index: 632882 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.9036. Min Range: -0.9036

Max Act: 0.5350. Min Act: -0.0000

Data Index: 415914 (C4 (Web Text))

Max Activating Token Index: 801