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

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

Neuron 4510 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: 2.0554. Min Range: -2.0554

Max Act: 2.0554. Min Act: -0.0000

Data Index: 413817 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.8296. Min Act: -0.0000

Data Index: 162836 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.7438. Min Act: -0.0000

Data Index: 1020499 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1067486 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.6436. Min Act: -0.0000

Data Index: 627775 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.6344. Min Act: -0.0000

Data Index: 320493 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5239. Min Act: -0.0000

Data Index: 147069 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5849. Min Act: -0.0000

Data Index: 583451 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5613. Min Act: -0.0000

Data Index: 27096 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5245. Min Act: -0.0000

Data Index: 516843 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1589450 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5097. Min Act: -0.0000

Data Index: 835696 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.4671. Min Act: -0.0000

Data Index: 607830 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.4794. Min Act: -0.0000

Data Index: 392577 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5526. Min Act: -0.0000

Data Index: 276315 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.4632. Min Act: -0.0000

Data Index: 27156 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.2934. Min Act: -0.0000

Data Index: 551446 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1460225 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1096703 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 2.0554. Min Range: -2.0554

Max Act: 1.4731. Min Act: -0.0000

Data Index: 805033 (C4 (Web Text))

Max Activating Token Index: 318