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

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

Neuron 1185 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1115995 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6923. Min Act: -0.0000

Data Index: 29482 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6571. Min Act: -0.0000

Data Index: 381097 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1311453 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7059. Min Act: -0.0000

Data Index: 691729 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6436. Min Act: -0.0000

Data Index: 978052 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1129447 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5608. Min Act: -0.0000

Data Index: 781596 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6152. Min Act: -0.0000

Data Index: 401472 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6139. Min Act: -0.0000

Data Index: 199135 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6009. Min Act: -0.0000

Data Index: 123799 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1204390 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6474. Min Act: -0.0000

Data Index: 218326 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1199333 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5922. Min Act: -0.0000

Data Index: 773748 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1276423 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5885. Min Act: -0.0000

Data Index: 974632 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5895. Min Act: -0.0000

Data Index: 633673 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6078. Min Act: -0.0000

Data Index: 16959 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6059. Min Act: -0.0000

Data Index: 97831 (C4 (Web Text))

Max Activating Token Index: 451