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

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

Neuron 2300 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6702. Min Range: -2.6702

Max Act: 2.6702. Min Act: -0.0000

Data Index: 1198066 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 2.6702. Min Range: -2.6702

Max Act: 2.2648. Min Act: -0.0000

Data Index: 846913 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 2.6702. Min Range: -2.6702

Max Act: 2.1308. Min Act: -0.0001

Data Index: 526879 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.7934. Min Act: -0.0000

Data Index: 465923 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 2.6702. Min Range: -2.6702

Max Act: 2.0751. Min Act: -0.0000

Data Index: 621894 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.9619. Min Act: -0.0000

Data Index: 281504 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 2.6702. Min Range: -2.6702

Max Act: 2.1880. Min Act: -0.0001

Data Index: 745894 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.7328. Min Act: -0.0001

Data Index: 849903 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 2.6702. Min Range: -2.6702

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1226862 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1123893 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.7512. Min Act: -0.0001

Data Index: 152915 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1081481 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.9054. Min Act: -0.0000

Data Index: 353920 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.8683. Min Act: -0.0000

Data Index: 1189700 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.6877. Min Act: -0.0000

Data Index: 679264 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.7647. Min Act: -0.0000

Data Index: 742295 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1211134 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.7633. Min Act: -0.0001

Data Index: 1072566 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.8477. Min Act: -0.0000

Data Index: 206510 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 2.6702. Min Range: -2.6702

Max Act: 1.6466. Min Act: -0.0000

Data Index: 749122 (C4 (Web Text))

Max Activating Token Index: 397