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

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

Neuron 3103 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.9559. Min Act: -0.0000

Data Index: 256565 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.6411. Min Act: -0.0000

Data Index: 859546 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.6765. Min Act: -0.0000

Data Index: 214515 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.6448. Min Act: -0.0000

Data Index: 940817 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.4239. Min Act: -0.0000

Data Index: 165882 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.6743. Min Act: -0.0000

Data Index: 1357491 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.4827. Min Act: -0.0000

Data Index: 715946 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.3678. Min Act: -0.0000

Data Index: 73515 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.4234. Min Act: -0.0000

Data Index: 119085 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.0364. Min Act: -0.0000

Data Index: 1312949 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.1150. Min Act: -0.0000

Data Index: 633044 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.1507. Min Act: -0.0000

Data Index: 550261 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.9740. Min Act: -0.0000

Data Index: 272208 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 2.9559. Min Range: -2.9559

Max Act: 2.0749. Min Act: -0.0000

Data Index: 337953 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.9512. Min Act: -0.0000

Data Index: 25339 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.9413. Min Act: -0.0000

Data Index: 1147802 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.9116. Min Act: -0.0000

Data Index: 162832 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.9147. Min Act: -0.0000

Data Index: 60611 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1257927 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.9559. Min Range: -2.9559

Max Act: 1.8744. Min Act: -0.0000

Data Index: 871943 (C4 (Web Text))

Max Activating Token Index: 556