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

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

Neuron 1512 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1421802 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1579520 (Python Code)

Max Activating Token Index: 904

Text #2

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1600459 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1430545 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1626217 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1161096 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6099. Min Act: -0.0000

Data Index: 905543 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1415391 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6756. Min Act: -0.0000

Data Index: 685623 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6280. Min Act: -0.0000

Data Index: 764900 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6456. Min Act: -0.0000

Data Index: 729269 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6589. Min Act: -0.0000

Data Index: 302590 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1644871 (Python Code)

Max Activating Token Index: 330

Text #13

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6296. Min Act: -0.0000

Data Index: 871080 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1591598 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1489548 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.5616. Min Act: -0.0000

Data Index: 31560 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.5454. Min Act: -0.0000

Data Index: 749698 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.5533. Min Act: -0.0000

Data Index: 721059 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1360258 (Python Code)

Max Activating Token Index: 859