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

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

Neuron 2636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.0573. Min Act: -0.0002

Data Index: 528266 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1772. Min Act: -0.0002

Data Index: 191287 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.9167. Min Act: -0.0002

Data Index: 1278695 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1309. Min Act: -0.0002

Data Index: 1141697 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.9739. Min Act: -0.0002

Data Index: 822661 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7920. Min Act: -0.0002

Data Index: 183304 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.8828. Min Act: -0.0002

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.9392. Min Act: -0.0002

Data Index: 240762 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.3354. Min Act: -0.0002

Data Index: 1241079 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.6688. Min Act: -0.0002

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.6398. Min Act: -0.0002

Data Index: 872253 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.6512. Min Act: -0.0002

Data Index: 174296 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 1062466 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 836273 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 93846 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 684174 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 787081 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 1011373 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 396546 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.3354. Min Range: -3.3354

Max Act: 2.7721. Min Act: -0.0002

Data Index: 899297 (C4 (Web Text))

Max Activating Token Index: 5