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

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

Neuron 5941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.4761. Min Act: -0.0001

Data Index: 745171 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2023. Min Act: -0.0000

Data Index: 193308 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.9733. Min Act: -0.0000

Data Index: 243613 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1345911 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.8587. Min Act: -0.0000

Data Index: 727058 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.9071. Min Act: -0.0000

Data Index: 726277 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 3.4761. Min Range: -3.4761

Max Act: 2.0442. Min Act: -0.0000

Data Index: 256032 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.5843. Min Act: -0.0000

Data Index: 401268 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.6271. Min Act: -0.0000

Data Index: 257365 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.4909. Min Act: -0.0000

Data Index: 213371 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.5511. Min Act: -0.0000

Data Index: 130523 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.5246. Min Act: -0.0000

Data Index: 504571 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.5364. Min Act: -0.0000

Data Index: 490916 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1250925 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.5439. Min Act: -0.0000

Data Index: 616433 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.4886. Min Act: -0.0000

Data Index: 865222 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.3405. Min Act: -0.0000

Data Index: 968840 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.3762. Min Act: -0.0000

Data Index: 99646 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.5253. Min Act: -0.0000

Data Index: 968076 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 3.4761. Min Range: -3.4761

Max Act: 1.3944. Min Act: -0.0000

Data Index: 119266 (C4 (Web Text))

Max Activating Token Index: 815