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

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

Neuron 1959 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.5286. Min Act: -0.0001

Data Index: 674003 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.5823. Min Act: -0.0001

Data Index: 771166 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3856. Min Act: -0.0001

Data Index: 176980 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3454. Min Act: -0.0001

Data Index: 1309945 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3097. Min Act: -0.0001

Data Index: 907986 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3966. Min Act: -0.0001

Data Index: 648112 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.4274. Min Act: -0.0001

Data Index: 1512476 (Python Code)

Max Activating Token Index: 667

Text #7

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.2949. Min Act: -0.0001

Data Index: 254779 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.2649. Min Act: -0.0001

Data Index: 1148739 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1766. Min Act: -0.0001

Data Index: 930683 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.2644. Min Act: -0.0001

Data Index: 935903 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3365. Min Act: -0.0001

Data Index: 1249862 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3243. Min Act: -0.0001

Data Index: 1063943 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.2332. Min Act: -0.0001

Data Index: 990126 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.3562. Min Act: -0.0001

Data Index: 373296 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1827. Min Act: -0.0001

Data Index: 382099 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1459. Min Act: -0.0001

Data Index: 907819 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1115. Min Act: -0.0001

Data Index: 39273 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1919. Min Act: -0.0001

Data Index: 495738 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.5823. Min Range: -1.5823

Max Act: 1.1562. Min Act: -0.0001

Data Index: 758817 (C4 (Web Text))

Max Activating Token Index: 2