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

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

Neuron 4183 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: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0000

Data Index: 32413 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1106093 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1350772 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0820. Min Act: -0.0000

Data Index: 525671 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0555. Min Act: -0.0000

Data Index: 448363 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0683. Min Act: -0.0000

Data Index: 783862 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0655. Min Act: -0.0000

Data Index: 705163 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0629. Min Act: -0.0000

Data Index: 104395 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0690. Min Act: -0.0000

Data Index: 562765 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0641. Min Act: -0.0001

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0622. Min Act: -0.0000

Data Index: 149258 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0572. Min Act: -0.0000

Data Index: 501526 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1037101 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0569. Min Act: -0.0000

Data Index: 27363 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0688. Min Act: -0.0000

Data Index: 112491 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1358452 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0620. Min Act: -0.0000

Data Index: 511447 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0628. Min Act: -0.0000

Data Index: 905369 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0521. Min Act: -0.0000

Data Index: 756793 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0662. Min Act: -0.0000

Data Index: 693755 (C4 (Web Text))

Max Activating Token Index: 872