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

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

Neuron 1728 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.9191. Min Act: -0.0000

Data Index: 938331 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.9838. Min Act: -0.0000

Data Index: 200030 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.9140. Min Act: -0.0000

Data Index: 495110 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1025510 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7454. Min Act: -0.0000

Data Index: 762254 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8107. Min Act: -0.0000

Data Index: 952080 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7497. Min Act: -0.0000

Data Index: 662849 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7547. Min Act: -0.0000

Data Index: 586025 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7558. Min Act: -0.0000

Data Index: 342463 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7211. Min Act: -0.0000

Data Index: 145617 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1271271 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6262. Min Act: -0.0000

Data Index: 318355 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7493. Min Act: 0.0001

Data Index: 1628689 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6547. Min Act: -0.0000

Data Index: 392532 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1041704 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6177. Min Act: -0.0000

Data Index: 23906 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.5889. Min Act: -0.0000

Data Index: 828620 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1291090 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6025. Min Act: -0.0000

Data Index: 709690 (C4 (Web Text))

Max Activating Token Index: 1011