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

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

Neuron 4474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.8128. Min Act: -0.0000

Data Index: 564305 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1206923 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7061. Min Act: -0.0000

Data Index: 145058 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7757. Min Act: -0.0000

Data Index: 793722 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7597. Min Act: -0.0000

Data Index: 404623 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7128. Min Act: -0.0000

Data Index: 578690 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7395. Min Act: -0.0000

Data Index: 462505 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1255344 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6313. Min Act: -0.0000

Data Index: 641376 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6881. Min Act: -0.0000

Data Index: 912491 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6580. Min Act: -0.0000

Data Index: 271410 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6536. Min Act: -0.0000

Data Index: 466923 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1208760 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6803. Min Act: -0.0000

Data Index: 162087 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6782. Min Act: -0.0000

Data Index: 211385 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6403. Min Act: -0.0000

Data Index: 332522 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6594. Min Act: -0.0000

Data Index: 473129 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6467. Min Act: -0.0000

Data Index: 223035 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6562. Min Act: -0.0000

Data Index: 140169 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6595. Min Act: -0.0000

Data Index: 508317 (C4 (Web Text))

Max Activating Token Index: 747