Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3480 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5676. Min Act: -0.0003

Data Index: 294850 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5262. Min Act: -0.0003

Data Index: 1241725 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5606. Min Act: -0.0003

Data Index: 691055 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5551. Min Act: -0.0003

Data Index: 1159480 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5412. Min Act: -0.0003

Data Index: 744378 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4642. Min Act: -0.0003

Data Index: 340957 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5350. Min Act: -0.0003

Data Index: 515508 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4536. Min Act: -0.0003

Data Index: 965504 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5331. Min Act: -0.0003

Data Index: 503540 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5227. Min Act: -0.0003

Data Index: 406712 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5044. Min Act: -0.0004

Data Index: 155246 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4527. Min Act: -0.0003

Data Index: 1338692 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5132. Min Act: -0.0003

Data Index: 1289271 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5135. Min Act: -0.0003

Data Index: 632453 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4936. Min Act: -0.0003

Data Index: 470473 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4615. Min Act: -0.0003

Data Index: 770969 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4599. Min Act: -0.0003

Data Index: 91309 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5094. Min Act: -0.0003

Data Index: 1089545 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4737. Min Act: -0.0003

Data Index: 1117737 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4887. Min Act: -0.0003

Data Index: 1085074 (C4 (Web Text))

Max Activating Token Index: 7