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

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

Neuron 1430 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: 2.5733. Min Range: -2.5733

Max Act: 2.5733. Min Act: -0.0000

Data Index: 705178 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.9098. Min Act: -0.0000

Data Index: 354705 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.0106. Min Act: -0.0000

Data Index: 328876 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.9054. Min Act: -0.0000

Data Index: 615317 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.8556. Min Act: -0.0000

Data Index: 585867 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.7768. Min Act: -0.0000

Data Index: 10819 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1182358 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.7700. Min Act: -0.0000

Data Index: 627593 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.6492. Min Act: -0.0000

Data Index: 242616 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.5449. Min Act: -0.0000

Data Index: 623714 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.5372. Min Act: -0.0000

Data Index: 188342 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.4402. Min Act: -0.0000

Data Index: 117860 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.7171. Min Act: -0.0000

Data Index: 250090 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.6459. Min Act: -0.0000

Data Index: 996031 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.5848. Min Act: -0.0000

Data Index: 636436 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1055655 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.5914. Min Act: -0.0000

Data Index: 120353 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.5753. Min Act: -0.0000

Data Index: 261802 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.6695. Min Act: -0.0000

Data Index: 678955 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 2.5733. Min Range: -2.5733

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1108595 (C4 (Web Text))

Max Activating Token Index: 18